PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception Paper • 2606.28322 • Published 30 days ago • 42
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously Paper • 2606.31551 • Published 26 days ago • 24
Ornith-1.0 Collection Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 28 days ago • 354
Autodata: An agentic data scientist to create high quality synthetic data Paper • 2606.25996 • Published Jun 24 • 18
Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations Paper • 2606.15641 • Published Jun 14 • 5
🚀 Qwen-MTP Collection ⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated 26 days ago • 34
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction Paper • 2606.18558 • Published Jun 17 • 53
Macaron-A2UI: A Model for Generative UI in Personal Agents Paper • 2605.24830 • Published May 24 • 84
SkillOpt: Executive Strategy for Self-Evolving Agent Skills Paper • 2605.23904 • Published May 22 • 262
OpenEnv India Hackathon top 100 Collection Top 100 Space submissions from the OpenEnv India Hackathon. • 98 items • Updated Jun 24 • 9
view article Article DeepSeek-V4: a million-token context that agents can actually use burtenshaw • Apr 24 • 52
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 919
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation Paper • 2603.25804 • Published Mar 26 • 30
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents Paper • 2603.24440 • Published Mar 25 • 99