AI.info

Latest Research — Page 53

Browse Latest Research on AI.info.

• Conformal Coverage Guarantees for Any Video Temporal Grounder
• Enhancing Visual Domain Robustness in Behaviour Cloning via Saliency-Guided Augmentation
• FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
• Learning Parameterized Skills from Demonstrations
• Generative Retrieval for Unsupervised Text-Based Person Search
• Exploring Federated Learning for Thermal Urban Feature Segmentation -- A Comparison of Centralized and Decentralized Approaches
• Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design
• RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning
• Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting
• Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
• Cross-lingual Biography Enrichment via Claim Extraction and Alignment
• ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
• Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
• Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts
• The Impact of Concept Explanations and Interventions on Human-Machine Collaboration
• A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
• DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting
• RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
• Panda: Test-Time Adaptation with Negative Data Augmentation
• ADAM Optimization with Adaptive Batch Selection
• Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study
• Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding
• Dynamic Haven Selection for Multi-Agent Pickup and Delivery in Constrained Warehouses
• UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
• Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
• Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics
• VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models
• Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
• Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation
• A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
• TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models
• What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom
• Surrogate Neural Architecture Codesign Package (SNAC-Pack)
• VideoNorms: Benchmarking Cultural Awareness of Video Language Models
• Effectiveness of Using Remote Laboratory in Promoting Simulation and Verification Tools
• DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments
• You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals
• TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
• Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination Detection