Vorch-Omni: Multi-Task Orchestration of Sight and Sound
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
On-Policy Delta Distillation for Multilingual Math Reasoning
Predicting Task Difficulty Without Rollouts
ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution
Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding
Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning
Subliminal Learning is Non-Semantic Distillation
Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation
Sparse Mutual Information Graph Averaging for Improving Random Indexing Embeddings
LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World…
G$^2$ARD-GS: Geometry-Guided Anchor-Regularized Gaussian Splatting Distillation
Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability f…
F$^2$Agent: Financial Fusion of Agentic Intelligence for Multimodal Trading
Potential Matching Optimal Transport: Continuous Normalizing Flows for Exact $p$-Wasserst…
Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Ma…
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploit…
Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Ma…
ALTER: Modeling Longitudinal Changes via Regional Differencing for 3D CT Report Generation
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Uncertainty-Aware World Model for Aerial Image-Goal Navigation
How Much Reconstruction Does Quantum Machine Learning Need? Late Fusion of Independently …
Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs
StepReflect: Structured UI Transition Reflection for Mobile GUI Agents
The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions
SimMOF: AI agent for Automated MOF Simulations
MemFly: On-the-Fly Memory Optimization via Information Bottleneck
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critic…
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning