Qi Fan

fanqiNO1's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 8 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 12 days ago • 188

upvoted 2 papers 11 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 12 days ago • 137

RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation

Paper • 2609.16900 • Published 14 days ago • 48

upvoted 2 papers 14 days ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 15 days ago • 247

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 15 days ago • 430

authored 2 papers 27 days ago

LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

Paper • 2608.16185 • Published Aug 18

CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language

Paper • 2609.00058 • Published 30 days ago • 1

upvoted a paper 27 days ago

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published 29 days ago • 315

upvoted a paper about 2 months ago

Self-Evolving Embodied Agents via Skill-Harness Evolution

Paper • 2608.11350 • Published Aug 11 • 15

upvoted a paper 2 months ago

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Paper • 2607.21653 • Published Jul 22 • 34

upvoted a paper 3 months ago

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Paper • 2607.05147 • Published Jul 6 • 51

upvoted a paper 5 months ago

Qwen3.5-Omni Technical Report

Paper • 2604.15804 • Published Apr 17 • 60

upvoted a paper 6 months ago

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published Mar 30 • 24

authored a paper 7 months ago

CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

Paper • 2603.02236 • Published Feb 13

upvoted 2 papers 8 months ago

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Paper • 2602.05400 • Published Feb 5 • 355

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published Feb 2 • 277

liked a model 8 months ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • 1T • Updated Apr 30 • 318k • • 2.88k

authored a paper 9 months ago

TimeBill: Time-Budgeted Inference for Large Language Models

Paper • 2512.21859 • Published Dec 26, 2025 • 25

upvoted a paper 9 months ago

TimeBill: Time-Budgeted Inference for Large Language Models

Paper • 2512.21859 • Published Dec 26, 2025 • 25

submitted a paper to Daily Papers 9 months ago

TimeBill: Time-Budgeted Inference for Large Language Models

Paper • 2512.21859 • Published Dec 26, 2025 • 25