TorchMorph: CUDA-accelerated Morphological Transforms
Paper • 2608.24738 • Published • 4
Yury Panikov
panikov
AI & ML interests
None yet
Recent Activity
upvoted a paper 7 days ago
TorchMorph: CUDA-accelerated Morphological Transforms upvoted a paper 7 days ago
MoTE: Mixture of Task Experts for Multi-Task Video Understanding upvoted a paper 7 days ago
Automata from Agent Traces: Failure and Next-Step PredictionOrganizations
None yet
upvoted 15
papers 7 days ago
MoTE: Mixture of Task Experts for Multi-Task Video Understanding
Paper • 2608.24763 • Published • 2
Automata from Agent Traces: Failure and Next-Step Prediction
Paper • 2608.23670 • Published • 5
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
Paper • 2608.23740 • Published • 7
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Paper • 2608.24794 • Published • 6
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
Paper • 2608.24845 • Published • 15
Meta^n: Recursive Self-Improvement through Emergent Depth
Paper • 2608.24735 • Published • 15
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Paper • 2608.23181 • Published • 34
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Paper • 2608.24876 • Published • 28
On-policy Distillation with Verifiable Reward
Paper • 2608.24696 • Published • 17
Best Practice Critic Optimization
Paper • 2608.23566 • Published • 18
On-Policy Self-Distillation in Diffusion Models
Paper • 2608.24646 • Published • 67
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
Paper • 2608.23041 • Published • 64
WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report
Paper • 2608.24053 • Published • 69
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Paper • 2608.20492 • Published • 111
upvoted 5
papers 8 days ago
Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection
Paper • 2608.21455 • Published • 3
ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts
Paper • 2608.22510 • Published • 5
Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA
Paper • 2608.22856 • Published • 4
The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search
Paper • 2608.23252 • Published • 4
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Paper • 2608.17336 • Published • 5