🟡 Notable
Other Signals
🟡 Helping disaster response teams turn AI into action across Asia — score 50
Sources: lab_blog/OpenAI
AI for Disaster Response in Asia: OpenAI Workshop with Gates Foundation
📄 New Papers
| Title | Category | Score | Link |
|---|---|---|---|
| Multi-Agent Dialectical Refinement for Enhanced Argument Classification | cs.AI | 0 | Open |
| Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development | cs.AI | 0 | Open |
| TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization | cs.AI | 0 | Open |
| KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study | cs.AI | 0 | Open |
| PeopleSearchBench: A Multi-Dimensional Benchmark for Evaluating AI-Powered People Search Platforms | cs.AI | 0 | Open |
| On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models | cs.AI | 0 | Open |
| Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning | cs.AI | 0 | Open |
| AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents | cs.AI | 0 | Open |
| Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding | cs.AI | 0 | Open |
| Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs | cs.AI | 0 | Open |
| Understanding Semantic Perturbations on In-Processing Generative Image Watermarks | cs.AI | 0 | Open |
| A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework | cs.AI | 0 | Open |
| Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs | cs.AI | 0 | Open |
| Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs | cs.AI | 0 | Open |
| Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation | cs.AI | 0 | Open |