M Saad Salman

MSS444's activity

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

upvoted 8 papers about 21 hours ago

RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

Paper • 2603.08561 • Published 8 days ago • 12

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

Paper • 2603.10145 • Published 7 days ago • 10

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

Paper • 2603.10160 • Published 7 days ago • 24

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 7 days ago • 114

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Paper • 2603.04597 • Published 13 days ago • 195

Automatic Generation of High-Performance RL Environments

Paper • 2603.12145 • Published 5 days ago • 6

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

Paper • 2603.10444 • Published 7 days ago • 10

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Paper • 2603.11863 • Published 5 days ago • 5

upvoted 2 papers 5 days ago

Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining

Paper • 2603.11103 • Published 7 days ago • 8

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training

Paper • 2603.12246 • Published 5 days ago • 4

upvoted 4 papers 6 days ago

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

Paper • 2603.05863 • Published 12 days ago • 5

Towards a Neural Debugger for Python

Paper • 2603.09951 • Published 7 days ago • 5

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness

Paper • 2603.09200 • Published 8 days ago • 5

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

Paper • 2603.09906 • Published 7 days ago • 67

upvoted 6 papers 7 days ago

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer

Paper • 2603.03583 • Published 14 days ago • 2

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

Paper • 2603.07777 • Published 9 days ago • 5

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

Paper • 2603.07779 • Published 9 days ago • 5

Agentic Critical Training

Paper • 2603.08706 • Published 8 days ago • 13

Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training

Paper • 2603.07223 • Published 10 days ago • 13

NLE: Non-autoregressive LLM-based ASR by Transcript Editing

Paper • 2603.08397 • Published 8 days ago • 21