Embarrassingly Simple Self-Distillation Improves Code Generation
Paper • 2604.01193 • Published • 34 •
6
Grant Singleton
grantsing
AI & ML interests
Computer vision, robotics, LLMs
Recent Activity
commentedon a paper about 16 hours ago
Embarrassingly Simple Self-Distillation Improves Code Generation commentedon a paper about 16 hours ago
RAGEN-2: Reasoning Collapse in Agentic RL commentedon a paper about 16 hours ago
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance EngineersOrganizations
None yet
commented 5
papers about 16 hours ago
RAGEN-2: Reasoning Collapse in Agentic RL
Paper • 2604.06268 • Published • 49 •
4
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
Paper • 2604.02648 • Published • 41 •
3
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 141 •
5
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 126 •
3
commented 5
papers 1 day ago
Leum-VL Technical Report
Paper • 2603.20354 • Published •
1
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 222 •
8
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 164 •
6
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Paper • 2604.06132 • Published • 107 •
5
Learning to Retrieve from Agent Trajectories
Paper • 2604.04949 • Published • 63 •
8
commented 5
papers 3 days ago
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Paper • 2604.04771 • Published • 110 •
4
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 195 •
12
InCoder-32B-Thinking: Industrial Code World Model for Thinking
Paper • 2604.03144 • Published • 222 •
3
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
Paper • 2603.28301 • Published • 77 •
5
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 95 •
4
commented 5
papers 4 days ago
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Paper • 2604.01658 • Published • 52 •
3
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 172 •
6
Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning
Paper • 2604.01152 • Published • 5 •
4
Therefore I am. I Think
Paper • 2604.01202 • Published • 30 •
4
NearID: Identity Representation Learning via Near-identity Distractors
Paper • 2604.01973 • Published • 29 •
3