AI.info

Latest Research — Page 74

Browse Latest Research on AI.info.

• Inducing Process Supervision from Outcome-Only Reinforcement Learning
• Scaling Image Geo-Localization to Continent Level
• Context-Aware Mixture of Domain Experts for Bodily Expression of Emotion in the Wild
• Is Agentic RAG worth it? An experimental comparison of RAG approaches
• ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation
• Agent Memory Is a Surface for Endogenous Authorization Laundering
• Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
• GranAlign: Granularity-Aware Alignment Framework for Zero-Shot Video Moment Retrieval
• Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning
• Multi-Window Temporal Analysis for Enhanced Arrhythmia Classification: Leveraging Long-Range Dependencies in Electrocardiogram Signals
• Attribute-Aware Controlled Product Generation with LLMs for E-commerce
• ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
• ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context
• Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning
• PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
• Stateless Language Agents: Scaling Long-Horizon Automated Research
• FairGU: Fairness-aware Graph Unlearning in Social Networks
• Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
• From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
• BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
• Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
• AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning
• AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
• Continual Learning at the Edge: An Agnostic IIoT Architecture
• Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
• An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation
• Learning When to Transfer: Reinforcement Learning for Carbon-Footprint Modeling in New Manufacturing Domains
• The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment
• AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition
• Improving the Physics of Video Generation with VJEPA-2 Reward Signal
• Context-aware Adaptive Visualizations for Critical Decision Making
• Factorized MLLM Embeddings for Composed Image Retrieval
• CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
• Think Before You Score: Thinking Reward Model for Visual Generation
• Aggregation Queries over Unstructured Text: Benchmark and Agentic Method
• DeFrame: Debiasing Large Language Models Against Framing Effects
• PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models
• Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees
• LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification
• DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference