AI.info

Latest Research — Page 7

Browse Latest Research on AI.info.

• When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
• Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds
• Unifying Stable Optimization and Reference Regularization in RLHF
• Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning
• Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans
• Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging
• Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
• TabReX : Tabular Referenceless eXplainable Evaluation
• Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
• Persona-E$^2$: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events
• TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
• Float8@2bits: Entropy Coding Enables Data-Free Model Compression
• TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin
• Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning
• Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
• PressTrack-HMR: Pressure-Based Top-Down Multi-Person Global Human Mesh Recovery
• Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes
• Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets
• From Decision Trees to Boolean Logic: A Fast and Unified SHAP Algorithm
• ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents
• DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
• EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning
• FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
• CombiGraph-Vis: A Curated Multimodal Olympiad Benchmark for Discrete Mathematical Reasoning
• Prime Agent: A Self-Improving RLM Harness
• Large Language Model Reasoning Failures
• ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research
• Context-weighted Discrete Flow Matching
• Annotation-Efficient Universal Honesty Alignment
• Alterbute: Editing Intrinsic Attributes of Objects in Images
• Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
• Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
• CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models
• Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams
• Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
• Tell Me: An LLM-powered Mental Well-being Assistant with RAG, Synthetic Dialogue Generation, and Agentic Planning
• A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries
• SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation
• Robustness study of the bio-inspired musculoskeletal arm robot based on the data-driven iterative learning algorithm
• Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance