AI.info
Latest Research — Page 102
Browse Latest Research on AI.info.
- InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
- Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability
- Physics-Constrained Denoising Autoencoders for Data-Scarce Wildfire UAV Sensing
- CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
- CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
- The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs
- Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books
- ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees
- Product distribution learning with imperfect advice
- VideoLucy: Deep Memory Backtracking for Long Video Understanding
- APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
- HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench
- Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
- Residual Diffusion Bridge Model for Image Restoration
- SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?
- International Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal Development
- JEPA-Anything: Learning Predictive Models across Different Worlds
- Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models
- NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
- TritonDFT: Automating DFT with a Multi-Agent Framework
- Task Success Is Not Enough: Side-effect-Aware Evaluation of Tool-Using Language Model Agents
- Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives
- Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations
- Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks
- TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
- Reinforced sequential Monte Carlo for amortised sampling
- More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
- Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference
- CRADLE Bench: A Clinician-Annotated Benchmark for Multi-Faceted Mental Health Crisis and Safety Risk Detection
- Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
- Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access
- Fast Data Attribution for Text-to-Image Models
- RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
- Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
- VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage
- Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
- SFE-O: An Ontology for Knowledge-Grounded AI in Supercritical CO$_2$ Biomass Extraction and Fractionation
- UCPO: Uncertainty-Aware Policy Optimization
- Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
- Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution