74% of Agent Coordination May Be Wasted Effort

Featured

• Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection score 5
  关键词(3): inference, vision-language, benchmark; 顶会接收: CVPR
• IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbation score 5
  关键词(2): diffusion, synthetic data; 顶会接收: CVPR
• Echoes of Ownership: Adversarial-Guided Dual Injection for Copyright Protection in MLLMs score 5
  关键词(3): deployment, fine-tuning, multimodal; 顶会接收: CVPR
• Hyperbolic Busemann Neural Networks score 5
  关键词(2): efficient, efficiency; 顶会接收: CVPR
• TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking score 5
  关键词(2): alignment, multimodal; 顶会接收: CVPR
• Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning score 5
  关键词(2): efficient, vision-language; 顶会接收: CVPR
• TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models score 5
  关键词(5): efficient, fine-tuning, reasoning, multimodal, embodied; 顶会接收: ICLR
• SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World score 5
  关键词(6): attention, agent, agents, reasoning, planning; 顶会接收: CVPR

Also Worth Noting

• Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification score 4
  关键词(1): diffusion; 顶会接收: CVPR
• Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding score 4
  关键词(1): fast; 顶会接收: CVPR
• When Coordination Is Avoidable: A Monotonicity Analysis of Organizational Tasks score 2
  关键词(2): agent, cost
• Transformers for dynamical systems learn transfer operators in-context score 2
  关键词(2): transformer, attention
• Systematic Analysis of Coupling Effects on Closed-Loop and Open-Loop Performance in Aerial Continuum Manipulators score 2
  关键词(2): evaluation, cost
• Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM score 2
  关键词(3): reasoning, benchmark, evaluation
• In-Context Planning with Latent Temporal Abstractions score 2
  关键词(5): efficient, quantization, transformer, planning, search
• Deep LoRA-Unfolding Networks for Image Restoration score 2
  关键词(4): efficient, efficiency, lightweight, deployment
• Watermarking LLM Agent Trajectories score 2
  关键词(4): agent, agents, reasoning, cost
• Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding score 2
  关键词(3): GRPO, reasoning, multimodal
• EDU-MATRIX: A Society-Centric Generative Cognitive Digital Twin Architecture for Secondary Education score 2
  关键词(4): alignment, agent, agents, safety
• Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse score 2
  关键词(2): inference, agentic
• HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing score 2
  关键词(8): deployment, inference, latency, fine-tuning, multimodal
• A Data-Driven Method to Map the Functional Organisation of Human Brain White Matter score 2
  关键词(2): attention, diffusion
• Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation score 2
  关键词(3): fast, deployment, agent