When Does Sparsity Mitigate the Curse of Depth in LLMs
Paper • 2603.15389 • Published • 5
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
When Does Sparsity Mitigate the Curse of Depth in LLMs upvoted a paper 2 days ago
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement LearningOrganizations
None yet
upvoted 10
papers 2 days ago
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
Paper • 2603.15611 • Published • 10
Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models
Paper • 2603.13985 • Published • 9
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
Paper • 2603.15500 • Published • 11
TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
Paper • 2603.12529 • Published • 18
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 71
Grounding World Simulation Models in a Real-World Metropolis
Paper • 2603.15583 • Published • 127
Attention Residuals
Paper • 2603.15031 • Published • 109
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
Paper • 2603.13594 • Published • 138
Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Paper • 2603.15653 • Published • 4
upvoted 8
papers 3 days ago
RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback
Paper • 2603.08561 • Published • 12
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Paper • 2603.10145 • Published • 11
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Paper • 2603.10160 • Published • 25
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 130
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Paper • 2603.04597 • Published • 204
Automatic Generation of High-Performance RL Environments
Paper • 2603.12145 • Published • 6
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
Paper • 2603.10444 • Published • 10
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges
Paper • 2603.11863 • Published • 6
upvoted 2
papers 7 days ago