M Saad Salman

MSS444's activity

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

upvoted 2 papers 31 minutes ago

Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation

Paper • 2602.07298 • Published 10 days ago • 1

AIDev: Studying AI Coding Agents on GitHub

Paper • 2602.09185 • Published 7 days ago • 2

upvoted a paper 32 minutes ago

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

Paper • 2602.14041 • Published 2 days ago • 4

upvoted 5 papers about 23 hours ago

Detecting RLVR Training Data via Structural Convergence of Reasoning

Paper • 2602.11792 • Published 5 days ago • 2

Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning

Paper • 2602.11748 • Published 5 days ago • 28

FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching

Paper • 2602.12829 • Published 4 days ago • 3

Intelligent AI Delegation

Paper • 2602.11865 • Published 5 days ago • 10

Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs

Paper • 2602.10388 • Published 6 days ago • 202

upvoted 12 papers 4 days ago

Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing

Paper • 2602.08741 • Published 8 days ago • 2

GoodVibe: Security-by-Vibe for LLM-Based Code Generation

Paper • 2602.10778 • Published 6 days ago • 2

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents

Paper • 2602.07900 • Published 9 days ago • 4

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL

Paper • 2602.03773 • Published 14 days ago • 9

Benchmarking Large Language Models for Knowledge Graph Validation

Paper • 2602.10748 • Published 6 days ago • 5

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

Paper • 2602.10231 • Published 6 days ago • 12

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning

Paper • 2602.11149 • Published 5 days ago • 12

DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning

Paper • 2602.11089 • Published 6 days ago • 18

How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning

Paper • 2602.10622 • Published 6 days ago • 26

Towards Autonomous Mathematics Research

Paper • 2602.10177 • Published 6 days ago • 34

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published 6 days ago • 174

Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use

Paper • 2602.11541 • Published 5 days ago • 3