AI.info

Latest Research — Page 56

Browse Latest Research on AI.info.

• Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
• Resource-constrained Amazons chess decision framework integrating large language models and graph attention
• DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset
• Stacking-Based Weighting for Large Language Bayes in M-Open Settings
• It Takes Workflows to Evolve Better Workflows
• Responsible Evaluation of AI for Mental Health
• X-Splat: Unified Gaussian Splatting for Joint RGB and X-ray 3D Reconstruction
• Scaling Spatial Reasoning in MLLMs through Programmatic Data Synthesis
• BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport
• Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
• Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning
• RECAP-Forcing: Retaining Content Appearances for Long Video Generation
• REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control
• Evaluating Large Language Models in Scientific Discovery
• Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
• 4D Reconstruction with Events & RGB
• AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs
• The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding
• Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols
• Generative Universal Verifier as Multimodal Meta-Reasoner
• In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents
• iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models
• When LLMs Forget What They Believe: Characterizing State Integrity Collapse in Long-Horizon Dialogues
• EgoExoMoCap: Distributed Ego-Exo Human Motion Capture
• MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding
• HumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form Video
• Rethinking On-policy Optimization for Query Augmentation
• CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception
• ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
• Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments
• Curiosity-driven RL for symbolic equation solving
• Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
• Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed
• Learning from Demonstrations via Capability-Aware Goal Sampling
• Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
• Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
• Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
• Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score
• Enoki: Efficient Multi-Level Hallucination Detection
• A-LAMP: Agentic LLM-Based Framework for Automated MDP Modeling and Policy Generation