AI.info

Latest Research — Page 10

Browse Latest Research on AI.info.

• Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
• PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
• NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers
• Do LiDAR Language Models Really Understand Spatio-temporal Relationships?
• Emergent Misalignment is Easy, Narrow Misalignment is Hard
• Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation
• Data Efficiency and Transfer Robustness in Biomedical Image Segmentation: A Study of Redundancy and Forgetting with Cellpose
• Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
• A Matter of Time: Revealing the Structure of Time in Vision-Language Models
• ERNet: Efficient Non-Rigid Registration Network for Point Sequences
• Stereo4DWalker: Learning 4D-aware Embodied Urban Navigation from Internet Stereo Videos
• MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
• dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
• Capabilities and Evaluation Biases of Large Language Models in Classical Chinese Poetry Generation: A Case Study on Tang Poetry
• MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
• Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems
• FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos
• Training-Free Character-Length Control in Summarization with Diffusion Language Models
• Is Finer Better? The Limits of Microscaling Formats in Large Language Models
• Exploration via Feature Perturbation in Contextual Bandits
• Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
• Mixed Precision Training of Neural ODEs
• PanicToCalm: A Proactive Counseling Agent for Panic Attacks
• SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
• rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment
• Scientific Knowledge-Guided Machine Learning for Vessel Power Prediction: A Comparative Study
• FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
• Towards Autonomous Mathematics Research
• CheatBench: Measuring Reward Gaming in AI Agents
• Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
• Measuring Aleatoric and Epistemic Uncertainty in LLMs: Empirical Evaluation on ID and OOD QA Tasks
• AutoTool: Efficient Tool Selection for Large Language Model Agents
• EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
• MV-MLM: Bridging Multi-View Mammography and Language for Breast Cancer Diagnosis and Risk Prediction
• From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps
• OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
• RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work
• Diffuse the object, keep its label: curating detector training data from a few unlabeled photographs via VLM-built 3D vegetation scenes
• Spiking Neural Networks for Continuous Control: Neuromorphic Reinforcement Learning in Conventional Computing