Demystifying When Pruning Works via Representation Hierarchies
Paper • 2603.24652 • Published • 17
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
Demystifying When Pruning Works via Representation Hierarchies upvoted a paper 5 days ago
In-Place Test-Time Training upvoted a paper 5 days ago
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code GenerationOrganizations
None yet
upvoted 5
papers 5 days ago
In-Place Test-Time Training
Paper • 2604.06169 • Published • 22
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Paper • 2604.03922 • Published • 51
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Paper • 2604.01591 • Published • 37
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Paper • 2604.04323 • Published • 37
upvoted 6
papers 6 days ago
Memory Intelligence Agent
Paper • 2604.04503 • Published • 51
Vero: An Open RL Recipe for General Visual Reasoning
Paper • 2604.04917 • Published • 28
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 29
ClawArena: Benchmarking AI Agents in Evolving Information Environments
Paper • 2604.04202 • Published • 35
LightThinker++: From Reasoning Compression to Memory Management
Paper • 2604.03679 • Published • 32
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 102
upvoted 9
papers 7 days ago
Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
Paper • 2604.01029 • Published • 7
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Paper • 2604.01161 • Published • 29
Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning
Paper • 2604.01152 • Published • 5
Executing as You Generate: Hiding Execution Latency in LLM Code Generation
Paper • 2604.00491 • Published • 6
Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
Paper • 2603.26233 • Published • 8
Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning
Paper • 2604.02007 • Published • 12
Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
Paper • 2604.00917 • Published • 17
UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
Paper • 2604.02190 • Published • 25
ASI-Evolve: AI Accelerates AI
Paper • 2603.29640 • Published • 25