M Saad Salman

MSS444's activity

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

upvoted 11 papers about 3 hours ago

What AI Red-Team Evaluations Can and Cannot Prove

Paper • 2607.21735 • Published 15 days ago • 2

Self-Evolving Coding Agents

Paper • 2608.03392 • Published 3 days ago • 4

Lossless Tensor Compression as Program Synthesis

Paper • 2608.02162 • Published 4 days ago • 9

Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance

Paper • 2608.00782 • Published 6 days ago • 14

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

Paper • 2608.03764 • Published 3 days ago • 22

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Paper • 2608.05139 • Published 2 days ago • 23

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 3 days ago • 29

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 2 days ago • 49

ChronoVision: Temporal Reasoning via Latent State Reconstruction

Paper • 2608.05631 • Published 1 day ago • 24

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 1 day ago • 17

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval

Paper • 2608.06060 • Published 1 day ago • 25

upvoted 9 papers 2 days ago

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Paper • 2608.00155 • Published 7 days ago • 12

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

Paper • 2608.02499 • Published 4 days ago • 24

DiffusionGemma Technical Report

Paper • 2608.00146 • Published 7 days ago • 33

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

Paper • 2608.01755 • Published 4 days ago • 139

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 4 days ago • 58

ExplainBench: Evaluating Code Explanations from Agents

Paper • 2607.26451 • Published 9 days ago • 12

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published 3 days ago • 20

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

Paper • 2608.04003 • Published 3 days ago • 28

PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning

Paper • 2608.01837 • Published 4 days ago • 37