HF Papers

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

2026-02-03

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

2026-02-03

Sparse Reward Subsystem in Large Language Models

Sparse Reward Subsystem in Large Language Models

2026-02-03

Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

2026-02-03

VoxServe: Streaming-Centric Serving System for Speech Language Models

VoxServe: Streaming-Centric Serving System for Speech Language Models

2026-02-03

An Empirical Study of World Model Quantization

An Empirical Study of World Model Quantization

2026-02-03

Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models

Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models

2026-02-03

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

2026-02-03

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability

2026-02-03

Enhancing Multi-Image Understanding through Delimiter Token Scaling

Enhancing Multi-Image Understanding through Delimiter Token Scaling

2026-02-03

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

2026-02-03

Interacted Planes Reveal 3D Line Mapping

Interacted Planes Reveal 3D Line Mapping

2026-02-03

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

2026-02-03

On the Limits of Layer Pruning for Generative Reasoning in LLMs

On the Limits of Layer Pruning for Generative Reasoning in LLMs

2026-02-03

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

2026-02-02

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

2026-02-02

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models

2026-02-02

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

2026-02-02

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

2026-02-02

Do Reasoning Models Enhance Embedding Models?

Do Reasoning Models Enhance Embedding Models?

2026-02-02