Results for “cross-functional-alignment”

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Evaluates automated metrics and vision-language models on identifying granular errors in detailed image descriptions and ranking paired descriptions against human judgments, using macro F1, pairwise accuracy, Spearman rank ρ, and Kendall's τ.

Scores generated image captions against reference captions and source images using the Polos metric, which is trained to align with human judgments and probes hallucination robustness and open-vocabulary evaluation.

Cardinality and model family jointly determine the encoding.

Pixtral 12B: A Frontier Multimodal Model

Kinetics-400: A Large Video Understanding Dataset

Perform fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O, DataFusion SQL, and pileup on Polars DataFrames via the polars-bio library, serving as a scalable alternative to bioframe and bedtools.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques for processing long documents and implementing efficient positional encodings.