AI.info

Latest Research — Page 70

Browse Latest Research on AI.info.

• GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
• Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning
• Meta Inverse Prompting for Video Generative Models
• ARCADE: A City-Scale Corpus for Fine-Grained Arabic Dialect Tagging
• DelTriC: A Novel Clustering Method with Accurate Outlier
• The AR Fairness Metamodel: A Structured Framework for Fairness Measures
• BikeScenes: LiDAR Semantic Segmentation for Bicycles
• Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
• PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting
• Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection
• Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
• Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning
• Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
• Closing the Modality Reasoning Gap for Speech Large Language Models
• AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
• Communication-Efficient Federated AUC Maximization with Cyclic Client Participation
• XCR-Bench: Benchmarking Cross-Cultural Reasoning in LLMs via Culture-Specific Items and Hall's Triad
• MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains
• The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
• IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking
• ToolHACE: A Dataset for Detecting Hallucinations in Tool-Based LLM Responses
• GLARE: Generating Listening Heads with Appropriate Reactions
• Registration is a Representation Problem: Solving Whole-Body PET/CT Registration
• Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
• Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
• Temporal Taxation Compounds Under Post-Training Compression of Whisper Models
• Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval
• Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
• CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning
• When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
• Delayed Feedback Modeling for Post-Click Gross Merchandise Volume Prediction: Benchmark, Insights and Approaches
• When to Trust Memory: Retrieval-Guided Probabilistic Spatiotemporal Forecasting under Distribution Shift
• Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure
• jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillation
• CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning
• Attention Is All You Need for KV Cache in Diffusion LLMs
• MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?
• When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
• SpecRoll: Fast-Slow Verifier-Feedback Adaptation for Speculative Reinforcement Learning Rollouts
• STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation