AI.info
Latest Research — Page 88
Browse Latest Research on AI.info.
- Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
- MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps
- Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models
- AgentOCR: Reimagining Agent History via Optical Self-Compression
- Unaligned Image Guided Denoising via Cross-modal Conditional Flow Matching
- Emergent Convergence in Multi-Agent LLM Annotation
- Protocol Choices Matter More Than the Aggregation Algorithm: Federated Learning for In-Hospital Mortality Prediction in Care-Unit and Multi-Hospital Federations
- AI use in American newspapers is widespread, uneven, and rarely disclosed
- Cowork-Gym: Synthesizing Interactive Work Environments at Scale
- Unlocking the Potential of Diffusion Language Models through Template Infilling
- Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression
- ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Driving
- AIDEN: Design and Pilot Study of an AI Assistant for the Visually Impaired
- Computable universal online learning
- Infinite-dimensional generative diffusions via Doob's h-transform
- Cross-Cultural Expert-Level Art Critique Evaluation with Vision-Language Models
- UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
- Directional Textual Inversion for Personalized Text-to-Image Generation
- Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
- ActionOPD: Distilling Decisions, Not Tokens
- FML-bench: Benchmarking Machine Learning Agents for Scientific Research
- EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
- Learning-based Adaptive Control of Quadruped Robots for Active Stabilization on Moving Platforms
- CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
- From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
- UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing
- Jev-ToM: Evaluating Theory of Mind in Typed Decision Models
- Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents
- Eye-Tracking, Mouse Tracking, Stimulus Tracking,and Decision-Making Datasets in Digital Pathology
- Neuromorphic Computing - An Overview
- YOLO-IOD: Towards Real Time Incremental Object Detection
- Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective
- Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels
- CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
- ECG-LLM -- training and evaluation of domain-specific large language models for electrocardiography
- Center-Outward q-Dominance: A Sample-Computable Proxy for Strong Stochastic Dominance in Multi-Objective Optimisation
- TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
- DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
- Learning 3D Editing without Paired Supervision via Generative Prior Distillation