M Saad Salman

MSS444's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 16 papers 1 day ago

Reward-free Alignment for Conflicting Objectives

Paper • 2602.02495 • Published 8 days ago • 2

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

Paper • 2602.03955 • Published 7 days ago • 7

Learning to Repair Lean Proofs from Compiler Feedback

Paper • 2602.02990 • Published 7 days ago • 25

Self-Hinting Language Models Enhance Reinforcement Learning

Paper • 2602.03143 • Published 7 days ago • 26

Rethinking the Trust Region in LLM Reinforcement Learning

Paper • 2602.04879 • Published 6 days ago • 30

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs

Paper • 2602.05258 • Published 5 days ago • 6

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

Paper • 2602.05547 • Published 5 days ago • 11

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better

Paper • 2602.05393 • Published 5 days ago • 6

Reinforced Attention Learning

Paper • 2602.04884 • Published 6 days ago • 21

Grounding and Enhancing Informativeness and Utility in Dataset Distillation

Paper • 2601.21296 • Published 12 days ago • 18

Semantic Search over 9 Million Mathematical Theorems

Paper • 2602.05216 • Published 5 days ago • 18

Privileged Information Distillation for Language Models

Paper • 2602.04942 • Published 6 days ago • 23

ProAct: Agentic Lookahead in Interactive Environments

Paper • 2602.05327 • Published 5 days ago • 23

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

Paper • 2602.05885 • Published 5 days ago • 26

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Paper • 2602.02474 • Published 8 days ago • 51

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning

Paper • 2602.06960 • Published 4 days ago • 9

upvoted 4 papers 6 days ago

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

Paper • 2602.02477 • Published 8 days ago • 9

LoopViT: Scaling Visual ARC with Looped Transformers

Paper • 2602.02156 • Published 8 days ago • 11

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

Paper • 2602.01511 • Published 8 days ago • 14

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

Paper • 2602.02486 • Published 8 days ago • 17