M Saad Salman

MSS444's activity

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

upvoted 2 papers 4 days ago

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

Paper • 2509.19284 • Published 4 days ago • 19

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published 4 days ago • 58

upvoted 4 papers 5 days ago

Synthetic bootstrapped pretraining

Paper • 2509.15248 • Published 10 days ago • 7

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Paper • 2509.16941 • Published 7 days ago • 19

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

Paper • 2509.16596 • Published 7 days ago • 11

Qwen3-Omni Technical Report

Paper • 2509.17765 • Published 5 days ago • 113

upvoted a paper 6 days ago

Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality

Paper • 2509.10402 • Published 15 days ago • 4

upvoted 3 papers 9 days ago

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

Paper • 2509.15185 • Published 9 days ago • 27

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

Paper • 2509.15194 • Published 9 days ago • 32

FlowRL: Matching Reward Distributions for LLM Reasoning

Paper • 2509.15207 • Published 9 days ago • 100

upvoted a paper 10 days ago

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

Paper • 2509.13761 • Published 11 days ago • 14

upvoted a paper 11 days ago

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving

Paper • 2509.12603 • Published 12 days ago • 8

upvoted a paper 13 days ago

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

Paper • 2509.07430 • Published 19 days ago • 3

upvoted 6 papers 17 days ago

Hunyuan-MT Technical Report

Paper • 2509.05209 • Published 22 days ago • 14

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

Paper • 2509.08755 • Published 17 days ago • 54

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published 17 days ago • 167

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

Paper • 2509.06923 • Published 19 days ago • 21

Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search

Paper • 2509.07969 • Published 18 days ago • 59

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Paper • 2509.07980 • Published 18 days ago • 96

upvoted a paper 19 days ago

Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

Paper • 2509.06493 • Published 19 days ago • 10