AI.info

Latest Research — Page 32

Browse Latest Research on AI.info.

• Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification
• BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References
• Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes
• A Contextual Analysis of Driver-Facing and Dual-View Video Inputs for Distraction Detection in Naturalistic Driving Environments
• Supervised Metric Regularization Through Alternating Optimization for Multi-Regime Physics-Informed Neural Networks
• Few-Shot-Based Modular Image-to-Video Adapter for Diffusion Models
• The Mouth is Not the Brain: Bridging Energy-Based World Models and Language Generation
• Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition
• When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
• CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection
• SUPRA-TEX: 3D Generation with Super-Aligned Texture
• Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
• Flow Matching Neural Processes
• Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning
• Which Tokens to Merge? Diffusion Dynamics for Efficient Image Generation
• Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection
• A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
• Axis-LoRA: Probing and Adapting Embedding Models for Personal-Memory Retrieval
• TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech
• A Federated Generalized Expectation-Maximization Algorithm for Mixture Models with an Unknown Number of Components
• Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation
• Predictive Coding Graphs are a Superset of Feedforward Neural Networks
• Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
• Democratizing Robot-Use Agents: A Unified Harness with Open Models
• GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development
• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models
• LatentPress: Context Compression Beyond Text and Vision
• Advances in Agentic Computer Graphics
• DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
• HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
• GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule
• Scaling Internal-State Policy-Gradient Methods for POMDPs
• POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
• TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
• Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation
• Differentiable Evolutionary Reinforcement Learning
• Flexing in 73 Languages: A Single Small Model for Multilingual Inflection
• Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
• Pattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning
• LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation