Everything is Context: Agentic File System Abstraction for Context Engineering
Paper • 2512.05470 • Published • 1 •
2
Grant Singleton
grantsing
AI & ML interests
Computer vision, robotics, LLMs
Recent Activity
commentedon a paper about 18 hours ago
Everything is Context: Agentic File System Abstraction for Context Engineering commentedon a paper about 18 hours ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability commentedon a paper about 18 hours ago
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion ModelsOrganizations
None yet
commented 5
papers about 18 hours ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 189 •
6
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
Paper • 2604.08546 • Published • 107 •
4
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 101 •
5
DMax: Aggressive Parallel Decoding for dLLMs
Paper • 2604.08302 • Published • 36 •
3
commented 5
papers 1 day ago
Embarrassingly Simple Self-Distillation Improves Code Generation
Paper • 2604.01193 • Published • 34 •
6
RAGEN-2: Reasoning Collapse in Agentic RL
Paper • 2604.06268 • Published • 52 •
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 • 213 •
6
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 141 •
4
commented 5
papers 3 days 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 • 224 •
8
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 291 •
6
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Paper • 2604.06132 • Published • 108 •
5
Learning to Retrieve from Agent Trajectories
Paper • 2604.04949 • Published • 63 •
8
commented 5
papers 4 days ago
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Paper • 2604.04771 • Published • 112 •
4
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 197 •
12
InCoder-32B-Thinking: Industrial Code World Model for Thinking
Paper • 2604.03144 • Published • 224 •
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 • 99 •
6