adu2021

@adu2021 source repo

1.2k skills
0 followers
1 day ago last updated

▌
Timeseries Scientist Agentic Forecasting · adu2021
Automate univariate time series forecasting through a four-agent system orchestrating preprocessing, model selection, validation, and reporting. Use when reducing manual effort in forecasting pipelines and improving reproducibility.

0 installs
▌
Tracealign Alignment Failure Attribution · adu2021
Trace unsafe LLM outputs back to conflicting beliefs in training data using suffix-array matching and Belief Conflict Index.

0 installs
▌
Truncated Step Level Retrieval Reasoning · adu2021
Improve credit assignment in retrieval-augmented reasoning by truncating trajectories at single decision points. Generate k samples sharing a common prefix, differing only at the next step to isolate variation and reduce gradient variance by T-fold on T-step tasks.

0 installs
▌
Unreasonable Scaling Computer Use Agents · adu2021
Scale computer-use agents from 30% to 72% success rate by generating parallel rollouts and selecting best trajectories through behavior narrative evaluation. Use when deploying desktop agents on complex, high-variance task scenarios.

0 installs
▌
Urbanllava Urban Multimodal Intelligence · adu2021
Unified MLLM processing four urban data types simultaneously: geospatial structures, trajectory information, satellite imagery, and street-view photos. Outperforms general-purpose models on 12-task urban benchmark with 31-375% improvements. Use for urban planning, traffic analysis, location intelligence, and smart city applications requiring integrated spatial reasoning.

0 installs
▌
Abstraction Augmented Continual Learning · adu2021
Replace standard supervised fine-tuning loss with a dual-objective loss that jointly optimizes over both concrete instances and their abstract representations (entity-masked versions), eliminating need for replay buffers and improving cumulative accuracy by 2-5% on continual learning benchmarks. Use when streaming data contains latent relational structure, catastrophic forgetting is problematic, and you want to maintain structural understanding without memory overhead.

0 installs
▌
Generalized Discrete Diffusion Snapshots · adu2021
Unify discrete diffusion for language by replacing token-wise uniform masking with generalized noising via rate matrices and snapshot latents, enabling semantic-aware forward processes. Demonstrates 1.16 BPC on Text8 and 7.65 perplexity on OpenWebText, beating autoregressive baselines; enables generalized noising processes over arbitrary vocabularies with efficient training aligned to standard architectures.

0 installs
▌
Multibind Attribute Misbinding Benchmark · adu2021
Evaluate multi-reference image generation fidelity using MultiBind's dimension-wise confusion framework. Detects cross-subject attribute errors that holistic metrics (FID, CLIP) miss, including drift (degradation), swap (permutation), dominance (interference), and blending (averaging). Protocol uses specialist models for face identity, appearance, pose, and expression; achieves reproducible failure diagnosis revealing severe binding failures in models appearing competitive on aggregate quality.

0 installs
▌
Uncha Hyperbolic Compositional Alignment · adu2021
Swap fixed entailment loss with uncertainty-guided piecewise-continuous formulation to improve part-to-whole compositional alignment in hyperbolic vision-language models by +3.0-3.1% on zero-shot classification. Use when training hyperbolic VLMs on part-object relationships and need better multi-object compositional understanding.

0 installs
▌
Visor Sparse Vision Language Interaction · adu2021
Optimize vision-language model inference by sparsifying the interactions between vision and language tokens instead of compressing images. Uses a dynamic policy to allocate visual computation per sample based on complexity, enabling a universal network across different compute budgets. Maintains high-resolution reasoning when needed. Use when deploying VLMs under varying compute constraints, need per-sample efficiency adaptation, or want to preserve fine visual details while reducing compute.

0 installs
▌
Agencybench Benchmarking The Frontiers Of · adu2021
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture long-horizon real-world scenarios. Moreover, the reliance on human-in-the-loop feedback for realistic tasks creates a scalability bottleneck, hindering automated rollout collection and evaluation. To bridge this gap, we introduce AgencyBench, a comprehensive bench...

0 installs
▌
Choreographing A World Of Dynamic Objects · adu2021
Research contribution advancing agent and reasoning capabilities through novel approaches to model development, training, and evaluation.

0 installs
▌
Dcpo Dynamic Clipping Policy Optimization · adu2021
DCPO eliminates zero-gradient dead zones in policy optimization by adaptively adjusting token-level clipping bounds based on prior probabilities and smoothing advantage standardization across cumulative training steps, achieving 28% improvement in effective response utilization and 10x reduction in token clipping ratio on mathematical reasoning benchmarks.

0 installs
▌
Dparallel Diffusion LLM Parallel Decoding · adu2021
Enable Diffusion Language Models to achieve 8.5x inference speedup (24-30 steps vs. 256) through certainty-forcing distillation that trains models to achieve simultaneous high confidence across multiple tokens. Use when optimizing inference latency for dLLM deployments.

0 installs
▌
Mixture Of Reasonings Adaptive Strategies · adu2021
Enable LLMs to autonomously select and apply diverse reasoning strategies without prompt engineering. Trains models with diverse thought templates covering 50-500 distinct reasoning approaches, achieving 2-13% improvements over baseline prompting methods.

0 installs
▌
Motion Stream Real Time Interactive Video · adu2021
Generate videos at 29 FPS with interactive motion control through teacher-student distillation of motion-conditioned video models, using sliding-window causal attention and attention sinks to maintain constant latency for indefinite-length generation.

0 installs
▌
Q Tuning Joint Pruning Efficient Training · adu2021
Dramatically reduce training data requirements (to 12.5% of original) while improving model performance using joint sample and token pruning guided by Error-Uncertainty plane diagnostics. Asymmetric pruning preserves calibration signals while removing redundant tokens from misconception examples.

0 installs
▌
Quantile Advantage Entropy Safe Reasoning · adu2021
Stabilize LLM reasoning training by replacing mean-based advantage baselines with K-quantile baselines, preventing both entropy collapse and explosion while improving performance on mathematical benchmarks through response-level gating and asymmetric sample weighting.

0 installs
▌
Rewardmap Sparse Rewards Visual Reasoning · adu2021
Improve multimodal LLMs on fine-grained visual reasoning tasks (e.g., reading transit maps) by decomposing training into stages: basic perception (VQA) -> simple reasoning -> complex spatial reasoning. Incorporates 'detail rewards' for intermediate visual understanding, bootstrapping models from simple to complex tasks while addressing sparse reward challenges.

0 installs
▌
Set Block Decoding Inference Acceleration · adu2021
Accelerate language model generation 3-5x by combining autoregressive and masked token prediction. Works via fine-tuning—no architectural changes needed. Parallel decode non-consecutive tokens with entropy-bounded sampling.

0 installs
▌
Single Image Iterative Subject Generation · adu2021
Personalize image generation and editing from a single reference image through inference-time LoRA optimization. Iteratively update model parameters based on visual similarity scores without training encoders or fine-tuning on multiple images.

0 installs
▌
Sparselora Contextual Sparsity Finetuning · adu2021
Accelerates LoRA fine-tuning 2.2× computationally and 1.6× wall-clock by leveraging contextual sparsity to compute gradients only for important weight channels. Uses training-free SVD sparsity estimation without full computation. Apply for efficient fine-tuning on memory-constrained GPUs or large-scale training scenarios.

0 installs
▌
Speceyes Speculative Agentic Acceleration · adu2021
Accelerate agentic multimodal LLMs via speculative execution without sacrificing accuracy. Use a lightweight tool-free MLLM to predict the main model's decisions and pre-compute tool calls before the main model confirms them. Cognitive gating enables the model to self-assess confidence. Achieves 1.1-3.35x speedup with accuracy improvements up to +6.7%. Use when reducing latency in multi-step agentic workflows, have compute budget for a second model, or need to parallelize tool execution with reasoning.

0 installs
▌
Universal Normal Embedding Gaussian Space · adu2021
Discover that generative models and vision encoders share an underlying approximately Gaussian latent space (UNE). Enable controllable image editing by operating on linear directions in diffusion noise space, revealing that semantic information is present without explicit supervision.

0 installs
▌
Aspo Advantage Shaping Policy Optimization · adu2021
Train LLMs to effectively integrate tools through advantage shaping, directly modifying advantage functions to guide policy without compromising training stability.

0 installs
▌
Bjudge Narrative Behavior Selection Agents · adu2021
Improve computer-use agent performance by running multiple rollouts and selecting the best trajectory using narrative-level reasoning. The Behavior Judge (BJudge) converts raw execution traces into behavior narratives, enabling intelligent trajectory selection that scales agent effectiveness beyond single-rollout limitations.

0 installs
▌
Cure Med Curriculum Informed Reinforcement · adu2021
While large language models (LLMs) have shown to perform well on monolingual mathematical and commonsense reasoning, they remain unreliable for multilingual medical reasoning applications, hindering their deployment in multilingual healthcare settings. We address this by first introducing CUREMED-BENCH, a high-quality multilingual medical reasoning dataset with open-ended reasoning queries with a single verifiable answer, spanning thirteen languages, including underrepresented languages such as ...

0 installs
▌
Fastcurl Curriculum Rl Efficient Reasoning · adu2021
Train efficient reasoning models using stage-wise context scaling and complexity-aware data selection. Achieves 49.6% accuracy on AIME 2024 while reducing training steps by 50% through alternating compress-extend cycles that progressively refine reasoning quality.

0 installs
▌
Mixture Of Recursions Adaptive Computation · adu2021
Build parameter-efficient models that assign different computation depths per token via learned routing, combining weight sharing with dynamic computation complexity. Use when you need to maximize model capacity within compute budgets or create models that allocate compute adaptively based on token complexity.

0 installs
▌
Modality Adaptive Reasoning Visualizations · adu2021
Enable small vision-language models to reason over diverse data types by converting latent embeddings into visual representations, achieving specialized performance without domain-specific training.

0 installs
▌
Paper2rebuttal A Multi Agent Framework For · adu2021
Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text generation problem, suffering from hallucination, overlooked critiques, and a lack of verifiable grounding. To address these limitations, we introduce $ extbf{RebuttalAgent}$, the first multi-agents framework that reframes rebuttal generation as an evidence-centric ...

0 installs
▌
Relayllm Efficient Reasoning Collaboration · adu2021
Enable small language models to dynamically invoke larger models at critical reasoning tokens rather than offloading entire queries. RelayLLM achieves 49.52% accuracy across benchmarks while invoking the large model for only 1.07% of tokens—98.2% cost reduction compared to non-collaborative approaches.

0 installs
▌
Retrofitted Recurrence Deeper Thinking Lms · adu2021
Convert pretrained non-recurrent language models into depth-recurrent variants through a curriculum of increasing recurrence—decoupling training compute from inference compute and improving performance at given inference budgets on reasoning tasks.

0 installs
▌
Rlve Scaling Rl With Adaptive Environments · adu2021
Scale RL training for language models by automatically adapting problem difficulty to match model capabilities using verifiable reward environments—achieving 3.37% absolute improvement on reasoning benchmarks through environment diversity rather than compute scaling alone.

0 installs
▌
Treevgr Visual Grounded Reasoning Evidence · adu2021
Train vision-language models to produce visually grounded reasoning by enforcing traceable evidence via bounding box localization, using a novel benchmark (TreeBench) and RL-based training with dual IoU rewards for both recall and precision.

0 installs
▌
Vla Rft World Model Reinforcement Robotics · adu2021
Fine-tune Vision-Language-Action models using learned world models as simulators, eliminating costly real-world or physics-simulation RL. Train robust robot policies in 400 steps via GRPO with model-generated verified rewards.

0 installs
▌
Abot Physworld Physics Aligned World Model · adu2021
Replace standard likelihood-based video diffusion training with decoupled physics discriminators and DPO post-training to suppress physically implausible behaviors (object penetration, anti-gravity motion) in robotic manipulation videos. Use when generating physics-realistic video predictions for embodied AI and want to maintain visual quality without physical violations.

0 installs
▌
Acot Vla Action Chain Of Thought For Vision · adu2021
Vision-Language-Action (VLA) models have emerged as essential generalist robot policies for diverse manipulation tasks, conventionally relying on directly translating multimodal inputs into actions via Vision-Language Model (VLM) embeddings. Recent advancements have introduced explicit intermediary reasoning, such as sub-task prediction (language) or goal image synthesis (vision), to guide action generation. However, these intermediate reasoning are often indirect and inherently limited in their...

0 installs
▌
Agentic Reasoning For Large Language Models · adu2021
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and dynamic environments. Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction. In this survey, we organize agentic reasoning along three complementary dimensions. First, we charact...

0 installs
▌
Ce Gppo Gradient Preserving Entropy Control · adu2021
Control policy entropy dynamics in RL by reweighting gradients from clipped tokens. CE-GPPO preserves out-of-clip gradients with beta parameters to stabilize exploration-exploitation balance, preventing entropy collapse while maintaining training stability in LLM fine-tuning.

0 installs
▌
Dflash Block Diffusion Speculative Decoding · adu2021
Accelerate LLM inference 6x by using block diffusion for parallel token drafting with tight coupling to the target model's hidden representations, achieving higher speedups than existing speculative methods without quality loss.

0 installs
▌
Ella Embodied Social Agents Lifelong Memory · adu2021
Enable autonomous embodied agents to function in 3D communities with structured memory systems. Combines semantic memory (scene graphs, knowledge graphs) and episodic memory (spatiotemporal experiences) for social intelligence and multi-agent coordination.

0 installs
▌
Epo Entropy Regularized Policy Optimization · adu2021
Stabilize multi-turn LLM agent training with entropy-regularized policy optimization that prevents exploration-exploitation cascade failures in sparse-reward environments through trajectory-level entropy regulation, historical smoothing, and adaptive phase-based weighting. Achieve up to 152% performance improvement on scientific reasoning tasks and 19.8% on embodied control by maintaining controlled entropy oscillations across 30+ interaction turns.

0 installs
▌
Gaea Geolocation Aware Conversational Model · adu2021
Build a conversational AI that combines image geolocalization with contextual geographical knowledge. GAEA enables users to query precise GPS locations from images while receiving conversational responses about places, their attributes, and regional context—outperforming GPT-4o by 7.2% on geography-aware visual QA tasks.

0 installs
▌
Infllm V2 Dense Sparse Switchable Attention · adu2021
Implement dense-sparse switchable attention enabling LLMs to scale from short to long sequences with 4× speedup and 98-99.7% performance retention, requiring no extra parameters by reusing pretrained attention weights through trainable sparse pattern selection.

0 installs
▌
Liberty A Causal Framework For Benchmarking · adu2021
Concept-based explanations quantify how high-level concepts (e.g., gender or experience) influence model behavior, which is crucial for decision-makers in high-stakes domains. Recent work evaluates the faithfulness of such explanations by comparing them to reference causal effects estimated from counterfactuals. In practice, existing benchmarks rely on costly human-written counterfactuals that serve as an imperfect proxy. To address this, we introduce a framework for constructing datasets contai...

0 installs
▌
Physrvg Physics Aware Unified Reinforcement · adu2021
Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of classical mechanics. While computer graphics and physics-based simulators can easily model such collisions using Newton formulas, modern pretrain-finetune paradigms discard the concept of object rigidity during pixel-level global denoising. Even perfectly correct math...

0 installs
▌
Reinforcement Distillation Negative Signals · adu2021
Extract maximum value from limited reasoning traces by leveraging both successful and failed examples through REINFORCE-style distillation.

0 installs
▌
Rerec Agent Development Release Engineering · adu2021
Apply software release engineering practices to self-improving LLM agents to achieve stable evolution. AgentDevel uses implementation-blind critique, executable diagnosis, and flip-centered gating to prevent regression while enabling auditable improvement trajectories.

0 installs
▌
Scalecua Cross Platform Computer Use Agents · adu2021
Build scalable open-source agents that autonomously operate graphical user interfaces across Windows, macOS, Linux, Android, iOS, and web platforms using large-scale cross-platform training data and vision-language models for GUI understanding, element grounding, and task completion.

0 installs
▌
T Lora Single Image Diffusion Customization · adu2021
Personalize diffusion models to learn a concept from a single image without overfitting by using timestep-dependent rank masking and orthogonal weight initialization, enabling faithful concept reproduction while maintaining text-guided control.

0 installs
▌
Tars Token Adaptive Hallucination Reduction · adu2021
Token-adaptive preference optimization framework using min-max formulation to reduce multimodal LLM hallucination. Achieves 50% hallucination reduction using min-max distributional robustness while preserving visual grounding.

0 installs
▌
Thinkmorph Interleaved Multimodal Reasoning · adu2021
Train unified models to generate interleaved reasoning steps combining text and image thoughts as complementary modalities, enabling adaptive behavior like autonomous mode-switching and superior test-time scaling for vision-centric tasks without requiring external guidance.

0 installs
▌
Webexplorer Long Horizon Web Agent Training · adu2021
Systematically train 8B web agents to solve complex information-seeking tasks through model-based exploration and long-to-short query evolution, achieving state-of-the-art performance via SFT+RL training pipeline with progressive context expansion to 128K tokens and 100 tool turns.

0 installs
▌
Realmaster Rendered To Photorealistic Video · adu2021
A single insight reframes sim-to-real video generation as decoupled structure-and-appearance transformation: use geometric conditioning to preserve structural fidelity while allowing free appearance transformation. This enables IC-LoRA training on pseudo-paired synthetic-real data constructed via sparse-to-dense propagation, eliminating the need for aligned real-world video capture. Trigger: When converting rendered 3D output to photorealistic video, apply structure-aware appearance transformation via geometric conditioning and sparse anchors to create training pairs without capturing real video.

0 installs
▌
Astroreason Bench Evaluating Unified Agentic · adu2021
Recent advances in agentic Large Language Models (LLMs) have positioned them as generalist planners capable of reasoning and acting across diverse tasks. However, existing agent benchmarks largely focus on symbolic or weakly grounded environments, leaving their performance in physics-constrained real-world domains underexplored. We introduce AstroReason-Bench, a comprehensive benchmark for evaluating agentic planning in Space Planning Problems (SPP), a family of high-stakes problems with heterog...

0 installs
▌
Clare Continual Learning For Vision Language · adu2021
To teach robots complex manipulation tasks, it is now a common practice to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for long-term operation in the real world, where robots must continually adapt to new tasks and environments while retaining the knowledge they have already acquired. Existing continual learning methods for robotics commonly require storing previous data (exemplars...

0 installs
▌
H Net Dynamic Chunking Hierarchical Sequence · adu2021
Eliminate fixed tokenization by learning data-dependent segmentation jointly with the model through dynamic chunking, matching BPE-tokenized Transformers at equivalent compute while showing improved robustness and better downstream task performance without vocabulary constraints.

0 installs
▌
Longcat Flash Thinking 2601 Technical Report · adu2021
Implement techniques from LongCat-Flash-Thinking-2601 Technical Report. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, including agentic search, agentic tool use, and tool-integrated reasoning

0 installs
▌
Omnitransfer All In One Framework For Spatio · adu2021
Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the rich spatio-temporal information inherent in videos, thereby limiting flexibility and generalization in video generation. To address these limitations, we propose OmniTransfer, a unified framework for spatio-temporal video transfer. It leverages multi-view info...

0 installs
▌
Sim Cot Supervised Implicit Chain Of Thought · adu2021
Train LLMs to reason implicitly with step-level supervision, stabilizing latent representations while preserving 2.3× inference speedup over explicit chain-of-thought. Addresses training collapse in implicit reasoning by aligning intermediate latent states with explicit reasoning steps through an auxiliary decoder during training, then removing the decoder for efficient inference.

0 installs
▌
Think Right Reasoning Allocation Calibration · adu2021
Dynamically allocate reasoning budgets per-task: 36.8% length reduction while improving accuracy 8.4% by learning which problems warrant deep reasoning vs. quick answers. Use when optimizing reasoning efficiency across variable-difficulty problems.

0 installs
▌
Unicom Compressed Multimodal Representations · adu2021
Compress visual embeddings into compact latent space for unified image understanding and generation. Combines attention-based compression with diffusion decoding to bridge comprehension and generation through a shared semantic bottleneck.

0 installs
▌
Adaptive Token Reduction Image Representation · adu2021
Adaptively prune visual tokens from vision encoders by reconstructing discarded features from retained ones, reducing computational cost by 50% while maintaining task performance on OCR and image understanding tasks.

0 installs
▌
Generalized Few Shot Point Cloud Segmentation · adu2021
Segment novel 3D point cloud classes with few support samples by combining dense but noisy pseudo-labels from 3D vision-language models with precise sparse few-shot annotations. GFS-VL adapts to new classes while retaining base class performance, using prototype-guided filtering and adaptive infilling strategies ideal for applications with limited labeled training data.

0 installs
▌
Medical Sam3 A Foundation Model For Universal · adu2021
Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited by severe domain shifts, the absence of privileged spatial prompts, and the need to reason over complex anatomical and volumetric structures. Here we present Medical SAM3, a foundation model for universal prompt-driven medical image segmentation, obtained by fu...

0 installs
▌
Mits Pointwise Mutual Information Tree Search · adu2021
Score reasoning paths using PMI to identify question-specific relevant steps without rollout simulations, enabling efficient tree search 12× faster than MCTS while improving reasoning accuracy.

0 installs
▌
Numina Lean Agent An Open And General Agentic · adu2021
Agentic systems have recently become the dominant paradigm for formal theorem proving, achieving strong performance by coordinating multiple models and tools. However, existing approaches often rely on task-specific pipelines and trained formal provers, limiting their flexibility and reproducibility. In this paper, we propose the paradigm that directly uses a general coding agent as a formal math reasoner. This paradigm is motivated by (1) A general coding agent provides a natural interface for ...

0 installs
▌
Toolprmbench Evaluating And Advancing Process · adu2021
Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models (PRMs) to provide step-level rewards, enabling more fine-grained monitoring. However, there is a lack of systematic and reliable evaluation benchmarks for PRMs in tool-using settings. In this paper, we introduce ToolPRMBench, a large-scale benchmark specifical...

0 installs
▌
Attnrl Attention Compass Reasoning Exploration · adu2021
Guide LLM exploration in reasoning tasks using attention patterns as navigation signals. This technique branches exploration from high-attention tokens (likely reasoning steps) and applies adaptive sampling to maintain effective gradients, significantly improving training efficiency for mathematical reasoning.

0 installs
▌
Behavior Knowledge Merge In Reinforced Agentic · adu2021
Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents from different tasks into a single generalist model. However, existing merging methods are designed for supervised fine-tuning (SFT), and they are suboptimal to preserve task-specific capabilities on RL-trained agentic models. The root is a task-vector mismatch ...

0 installs
▌
Being H05 Scaling Human Centric Robot Learning · adu2021
We introduce Being-H0.5, a foundational Vision-Language-Action (VLA) model designed for robust cross-embodiment generalization across diverse robotic platforms. While existing VLAs often struggle with morphological heterogeneity and data scarcity, we propose a human-centric learning paradigm that treats human interaction traces as a universal 'mother tongue' for physical interaction. To support this, we present UniHand-2.0, the largest embodied pre-training recipe to date, comprising over 35,000...

0 installs
▌
Calm Continuous Autoregressive Language Models · adu2021
Replace discrete token prediction with continuous vector prediction by training a high-fidelity autoencoder to compress K tokens into single latent vectors, enabling K-fold sequence length reduction while maintaining likelihood-free generation through energy-based scoring rules.

0 installs
▌
Direct Group Preference Optimization Diffusion · adu2021
Optimize diffusion models for preference alignment by learning directly from group-level preferences without stochastic policies, enabling efficient and stable training.

0 installs
▌
Fantasyvln Unified Multimodal Chain Of Thought · adu2021
Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while reasoning over long action sequences. Recent works, such as NavCoT and NavGPT-2, demonstrate the potential of Chain-of-Thought (CoT) reasoning for improving interpretability and long-horizon planning. Moreover, multimodal extensions like OctoNav-R1 and CoT-VLA further validate CoT as a promising pathway toward human-li...

0 installs
▌
Less Is More Recursive Reasoning Tiny Networks · adu2021
Achieve complex reasoning with minimal parameters using latent recursion in 2-layer networks. A 7M-parameter Tiny Recursive Model (TRM) solves Sudoku (87% accuracy), mazes (85%), and ARC-AGI with 0.01% the parameters of large LLMs via iterative latent refinement through 6+ recursive steps without fixed-point convergence requirements.

0 installs
▌
Locate Steer And Improve A Practical Survey Of · adu2021
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: 'Locate, Steer, and Improve.' We formally categorize Localizing (diagnosis) and Steering (intervention) met...

0 installs
▌
Prism Benchmarking Phone Realization In Speech · adu2021
Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis. Despite prolonged efforts in developing PR systems, current evaluations only measure surface-level transcription accuracy. We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception through intrinsic and extrinsic evaluation of PR systems. PRiSM standardizes transcription-based evaluation and assesses downst...

0 installs
▌
Reasoning Models Generate Societies Of Thought · adu2021
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform comparable instruction-tuned models on complex cognitive tasks, attributed to extended computation through longer chains of thought. Here we show that enhanced reasoning emerges not from extended computation alone, but from simulating multi-agent-like interactions -- a society of thought -- which enables diversification a...

0 installs
▌
Reliable Rl Evaluation Contamination Detection · adu2021
Detect and eliminate data contamination that invalidates RL benchmarks by measuring benchmark reconstruction ability. Implement clean evaluation datasets to distinguish genuine reasoning improvements from memorization. Use when validating RL training results or ensuring benchmark integrity for mathematical reasoning.

0 installs
▌
Truthrl Ternary Reward Hallucination Reduction · adu2021
Reduce LLM hallucinations by training with a ternary reward signal that distinguishes correct answers, hallucinations, and abstentions. This technique incentivizes truthfulness over accuracy-only metrics, enabling safer, more calibrated language models through GRPO-based optimization.

0 installs
▌
Aligning Agentic World Models Via Knowledgeable · adu2021
Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of the physical world. Consequently, while these agents implicitly function as world models, their simulations often suffer from physical hallucinations-generating plans that are logically sound but physically unexecutable. Existing alignment strategies predominantly rely on resource-intensive training or fine-tuning, which...

0 installs
▌
Paper Categorizer · adu2021 bundle
Categorize ML/AI research papers into 11 types based on their title and abstract. Returns structured JSON with a primary category, optional secondary categories, extractability rating, and rationale. Designed for the SkillXiv paper2skill pipeline as a triage step. Use this skill whenever the user wants to classify, categorize, sort, or triage research papers — whether a single paper or a batch. Also trigger when someone asks "what kind of paper is this?", wants to filter papers by type, or needs to decide which papers to prioritize for skill extraction.

0 installs
▌
Paper2skill · adu2021
Convert arXiv and ML/AI research papers into ready-to-use Claude agent skills in seconds — so anyone can apply cutting-edge techniques without reading the full paper. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, create a paper-to-skill pipeline, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting actionable knowledge from papers, building skill libraries from literature, making research practical for LLM agents, or systematically converting academic contributions into structured agent capabilities.

0 installs
▌
Paper2skill V0 0 3 · adu2021 bundle
Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers produce different types of usable knowledge. A single paper can yield multiple skills if it spans categories. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting actionable knowledge from papers, making research practical for LLM agents, or systematically converting academic contributions into structured agent capabilities.

0 installs
▌
Paper2skill Insight Driven · adu2021
Convert insight-driven papers into minimal reproducible recipes built around a single non-obvious observation. Extracts the key insight, why the problem seemed hard, and the minimal implementation. Use this skill when extracting skills from Category 6 (Insight-Driven) papers — 'Learning to See in the Dark'-style papers where one clever observation unlocks a seemingly hard problem.

0 installs
▌
Paper2skill Field Foundation · adu2021
Convert foundational papers that create new subfields into conceptual framework skills. Extracts problem definitions, vocabulary, founding experiments, and opened research directions. Use this skill when extracting skills from Category 8 (Field Foundation) papers — MAML-style paradigm-creating papers or 'Deep Learning' review-style papers that define entire research communities.

0 installs
▌
Paper2skill Survey Synthesis · adu2021
Convert survey and synthesis papers into field navigation guides. Extracts taxonomies, method selection decision trees, literature navigation heuristics, and open problems. Use this skill when extracting skills from Category 10 (Survey and Synthesis) papers — comprehensive reviews, position papers, tutorials, or roadmaps that organize a research landscape.

0 installs
▌
Paper2skill Paradigm Challenge · adu2021
Convert papers that disprove conventional wisdom into paradigm-challenge skills. Extracts the prior belief, the falsifying experiment, and the revised principle. Use this skill when extracting skills from Category 3 (Paradigm Challenge) papers — papers that say 'rethinking', 'revisiting', or 'do we really need X', where the core move is adversarial (proving the community wrong).

0 installs
▌
Paper2skill Scaling Efficiency · adu2021
Convert scaling and efficiency papers into practical resource planning guides. Extracts empirical scaling laws, compute-optimal allocation rules, and budget-performance trade-offs. Use this skill when extracting skills from Category 11 (Scaling and Efficiency) papers — Chinchilla-style scaling law papers, Flash Attention efficiency papers, or knowledge distillation studies.

0 installs
▌
Paper2skill Application Transfer · adu2021
Convert arXiv papers that apply ML techniques to real-world domains into application-transfer skills. Extracts problem formulation, domain adaptation gaps, and deployment recipes. Use this skill when extracting skills from Category 1 (Application Transfer) papers — papers about AlphaFold-style domain applications, robotics deployment, interdisciplinary ML crossings, or any paper where the novelty is in what was solved rather than the method itself.

0 installs
▌
Paper2skill Component Innovation · adu2021
Convert component innovation papers into drop-in replacement guides. Extracts what was swapped, why, conditions for when it helps, and the performance delta. Use this skill when extracting skills from Category 5 (Component Innovation) papers — BatchNorm-style papers, ResNet skip connections, new loss functions, or any paper proposing one elegant modification with outsized impact.

0 installs
▌
Paper2skill Mechanistic Analysis · adu2021
Convert mechanistic analysis papers into transferable analytical methodology skills. Extracts the research question, analytical instrument, controlled confounds, and practitioner implications. Use this skill when extracting skills from Category 9 (Mechanistic Analysis) papers — Network Dissection-style interpretability work or any paper whose goal is exploratory understanding of why something works.

0 installs
▌
Paper2skill Systematic Empiricism · adu2021
Convert systematic empiricism papers into ranked practitioner checklists. Extracts implementation tricks, hyperparameter findings, and design choice ablations with conditions of applicability. Use this skill when extracting skills from Category 4 (Systematic Empiricism) papers — '37 PPO details'-style papers, hyperparameter studies, or ablation-heavy guides that systematize scattered knowledge.

0 installs
▌
Dr Mas · adu2021
Enable stable multi-agent reinforcement learning by normalizing advantages per-agent rather than globally, preventing gradient-norm inflation in heterogeneous multi-agent systems.

0 installs
▌
Memfly · adu2021
Optimize agent long-term memory by treating it as an information bottleneck problem. Dynamically compress redundant information while preserving task-relevant content through semantic-symbolic-topological hybrid retrieval.

0 installs
▌
Paper2skill Research Infrastructure · adu2021
Convert research infrastructure papers into design pattern guides. Extracts capability gaps addressed, API design decisions, performance/usability trade-offs, and integration patterns. Use this skill when extracting skills from Category 7 (Research Infrastructure) papers — PyTorch-style framework papers, evaluation harness tooling, or any paper where the tool itself is the contribution.

0 installs
▌
Embed Rl · adu2021
Improve multimodal embeddings through RL-optimized reasoning that grounds evidence in retrievable visual cues. Frozen embedder provides stable rewards while reasoner generates evidential traceability CoT with text keywords, bounding boxes, and key frames.

0 installs
▌
Quco RAG · adu2021
Replace unreliable model-internal confidence signals with objective corpus statistics to decide when RAG retrieval is necessary. Pre-evaluates entity rarity in training data and verifies entity co-occurrence at runtime, triggering retrieval only when hallucination risk is high—improving reliability without per-model tuning.

0 installs
▌
Turn Ppo · adu2021
Stabilize multi-turn agent RL by shifting from token-level to turn-level MDPs. Reformulates states and actions at conversation-turn granularity, uses learned turn-level critics, and applies Generalized Advantage Estimation—eliminating misalignment that destabilizes GRPO training on long-horizon agentic tasks.

0 installs

1228 published skills · page 9 of 13