AI.info
Latest Research — Page 63
Browse Latest Research on AI.info.
- HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
- Parameter Reduction Improves Vision Transformers: A Comparative Study of Sharing and Width Reduction
- TaoMate-FVSR:Audio-Guided Facial Video Restoration
- LiM-YOLO: Less is More with Pyramid Level Shift for Ship Detection in Optical Remote Sensing
- LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance
- What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds
- SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension
- Controllable Generative Sandbox for Causal Inference
- Scalable Machine Learning Analysis of Parker Solar Probe Solar Wind Data
- MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation
- HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
- Glance: The Generator Is Its Own Reranker
- Reproducible Evaluation as the Substrate for Safe Prompt Compression in Production Agents
- Detecting AI Impostors: How Do Middle Schoolers Identify LLM Agents in a Live Collaborative Setting?
- InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
- MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
- Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
- StreamingThinker: Large Language Models Can Think While Reading
- Unifying Conformal Language Tasks with In-Context Ensembles
- ExpertAD: Enhancing Autonomous Driving Systems with Mixture of Experts
- Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models
- SwordRiding: A Unified Navigation Framework for Quadrotors in Unknown Complex Environments via Online Guiding Vector Fields
- FrameShield: Adversarially Robust Video Anomaly Detection
- UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
- Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
- Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention
- LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena
- Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
- Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective
- MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics
- Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration
- SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
- Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
- EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
- C-World: A Computer Use Agent Environment Creator
- When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue
- RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
- Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
- Py-DiSMech: A Scalable and Efficient Framework for Discrete Differential Geometry-Based Modeling and Control of Soft Robots
- Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation