AI.info

Latest Research — Page 16

Browse Latest Research on AI.info.

• Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
• Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation
• Persona-E$^2$: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events
• DecepEval: A Benchmark for Evaluating Deception in LLM Agents
• TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
• Float8@2bits: Entropy Coding Enables Data-Free Model Compression
• Know, then Draw: A New Learning Paradigm for Visual Generation
• InvestigationWorlds: An Agentic Environment for Legal Investigation
• SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection
• Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
• TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin
• GriDiT: Factorized Grid-Based Diffusion for Efficient Long Image Sequence Generation
• Dissimilarity-Based Markov Decision Processes for Stabilizing State Distributions
• MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
• Differentiable Inverse Graphics for Zero-shot Scene Reconstruction and Robot Grasping
• Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions
• Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
• MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images
• Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
• InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation
• 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
• KASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis Localization
• FORMSpoT: Revealing Fine-Scale Forest Disturbances from Nation-Wide 1.5 m Forest Canopy Height Time Series
• Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets
• dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
• From Decision Trees to Boolean Logic: A Fast and Unified SHAP Algorithm
• Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detection
• 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
• Splatography: Sparse multi-view dynamic Gaussian Splatting for filmmaking challenges
• DreamX: Video Diffusion Model is a Universal Latent Action Learner
• IQNN-CS: Interpretable Quantum Neural Network for Credit Scoring
• Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
• FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
• Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout
• Evaluating LLM Creativity through Long-Tail Performance