Convergent Evolution: How Different Language Models Learn Similar Number Representations
Paper • 2604.20817 • Published • 7
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
Convergent Evolution: How Different Language Models Learn Similar Number Representations upvoted a paper about 2 hours ago
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL upvoted a paper about 2 hours ago
Scaling Test-Time Compute for Agentic CodingOrganizations
None yet
upvoted 6
papers about 2 hours ago
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
Paper • 2604.17073 • Published • 9
Scaling Test-Time Compute for Agentic Coding
Paper • 2604.16529 • Published • 10
Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts
Paper • 2604.19835 • Published • 17
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Paper • 2604.13602 • Published • 29
Near-Future Policy Optimization
Paper • 2604.20733 • Published • 67
upvoted 12
papers 6 days ago
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Paper • 2604.13902 • Published • 61
Where does output diversity collapse in post-training?
Paper • 2604.16027 • Published • 22
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
Paper • 2604.15151 • Published • 15
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning
Paper • 2604.16029 • Published • 23
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
Paper • 2502.07408 • Published • 57
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
Paper • 2604.18584 • Published • 14
Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
Paper • 2604.18131 • Published • 9
Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play
Paper • 2604.17696 • Published • 6
When Can LLMs Learn to Reason with Weak Supervision?
Paper • 2604.18574 • Published • 24
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
Paper • 2604.17308 • Published • 22
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Paper • 2604.14258 • Published • 23
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Paper • 2604.18292 • Published • 80
upvoted 2
papers 10 days ago