AI.info

Latest Research — Page 58

Browse Latest Research on AI.info.

• PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise
• RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars
• Policy Learning with Abstention
• AI-Driven Disaster Response and Displacement Monitoring
• Seeing the Unseen: Zooming in the Dark with Event Cameras
• Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning
• Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
• One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
• VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
• MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
• What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization
• Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States
• Towards a Deterministic Math Solver for Clinical Language Models
• MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models
• Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models
• What Does Preference Learning Recover from Pairwise Comparison Data?
• Diagnosing Heteroskedasticity and Resolving Multicollinearity Paradoxes in Physicochemical Property Prediction
• M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
• Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression Detection
• AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
• Credal Ensemble Distillation for Uncertainty Quantification
• Controlled Decoding Attacks on Black-Box LLMs
• Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors
• What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
• RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures
• Decoupling Action from Egocentric Observation for World Simulation
• A Survey of Large Models in Sports
• MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
• SynQuE: Estimating Synthetic Dataset Quality Without Annotations
• When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
• The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
• Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
• Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance
• Code2World: A GUI World Model via Renderable Code Generation
• Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
• GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model
• Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems
• Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
• VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT
• Towards Integrating Uncertainty for Domain-Agnostic Segmentation