AI.info
Latest Research — Page 100
Browse Latest Research on AI.info.
- VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
- RefTon: Reference person shot assist virtual Try-on
- SLAP: Shortcut Learning for Abstract Planning
- M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
- Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
- ToC: Tree-of-Claims Search with Multi-Agent Language Models
- Gene Incremental Learning for Single-Cell Transcriptomics
- DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
- Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
- Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability
- Free Energy Mixer
- ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction
- Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
- FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data
- HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving
- E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search
- Factorized Learning for Temporally Grounded Video-Language Models
- PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
- Training-free Detection of AI-generated images via Cropping Robustness
- CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation
- WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment
- Hybrid Event Frame Sensors: Modeling, Calibration, and Simulation
- Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
- UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
- INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators
- Causality Guided Representation Learning for Cross-Style Hate Speech Detection
- TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
- From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation
- ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications
- Dr. Assistant: Enhancing Clinical Diagnostic Inquiry via Structured Diagnostic Reasoning Data and Reinforcement Learning
- SteuerLLM: Local specialized large language model for German tax law analysis
- Transporting Task Vectors across Different Architectures without Training
- ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
- OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks
- The Quest for Reliable Metrics of Responsible AI
- SCOPE: Selective Conformal Optimized Pairwise LLM Judging
- Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
- Mapping Semantic & Syntactic Relationships with Geometric Rotation
- From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge