AI.info

Latest Research — Page 21

Browse Latest Research on AI.info.

• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage
• When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors
• GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing
• Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
• Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction
• Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice
• HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks
• Structure Detection for Contextual Reinforcement Learning
• SOSControl: Enhancing Human Motion Generation through Saliency-Aware Symbolic Orientation and Timing Control
• Revisiting Node Affinity Prediction in Temporal Graphs
• LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
• ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups
• Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
• ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration
• Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
• Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
• Lossless Vocabulary Reduction for Auto-Regressive Language Models
• Know Thyself by Knowing Others: Learning Neuron Identity from Population Context
• A logical re-conception of neural networks: Hamiltonian bitwise part-whole architecture
• Light-X: Generative 4D Video Rendering with Camera and Illumination Control
• MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
• VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
• Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding
• EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
• Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
• VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness
• An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination
• Understanding Generalization in Role-Playing Models via Information Theory
• Rational Synthesizers or Heuristic Followers? Analyzing LLMs in RAG-based Question-Answering
• Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
• Multi-Head Low-Rank Attention
• Time-series Forecast for Indoor Zone Air Temperature with Long Horizons: A Case Study with Sensor-based Data from a Smart Building
• PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
• Analysis of Memory-Runtime Trade-offs in Caching Strategies for Genetic Programming Symbolic Regression
• PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update
• Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
• ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models
• Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
• Plain Transformers are Surprisingly Powerful Link Predictors
• MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks