AI.info

Latest Research — Page 69

Browse Latest Research on AI.info.

• 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
• Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
• Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions
• CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
• ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
• A Multi-Sensor Dataset for Monitoring the Operational Environment of Rail Vehicles
• Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
• RM-Distiller: Exploiting Generative LLM for Reward Model Distillation
• Multi-agent Self-triage System with Medical Flowcharts
• GuideFetch: A Task Coordination Framework for Concurrent Navigation and Object Retrieval in Assistive Robot Dogs
• SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics
• Generalized Linear Bandits with Memory
• Learning Subgroups with Maximum Treatment Effects without Causal Heuristics
• Rethinking Genomic Modeling Through Optical Character Recognition
• Training Language Models to Use Prolog as a Tool
• Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration
• Efficient Vision-Language Reasoning via Adaptive Token Pruning
• M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset
• Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers
• Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
• PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer
• Beyond "I Can't Help With That": How Child Safety Experts Evaluate AI Chatbot Safety
• Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
• FUSE: A Flow-based Mapping Between Shapes
• Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment
• Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis
• iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
• Global Feature Enhancing and Fusion Framework for Strain Gauge Time Series Classification
• Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
• Estimating Causal Effects in Gaussian Linear SCMs with Finite Data
• FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth
• Future Rendering $\neq$ Future Surface: A Benchmark and Dataset for Dynamic Surface Reconstruction Beyond the Observed Window
• Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
• LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs
• Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object Segmentation
• Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning
• CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation
• Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
• EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
• Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers