AI.info

Latest Research — Page 36

Browse Latest Research on AI.info.

• Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
• The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
• REFRAMED: Towards Realistic Audio Description Generation for Movies
• LORE: Jointly Learning the Intrinsic Dimensionality and Relative Similarity Structure From Ordinal Data
• Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
• Conditional Clifford-Steerable CNNs for PDE Modeling
• SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
• FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
• Exploring Conditions for Diffusion models in Robotic Control
• DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction
• Towards Robust and Fair Next Visit Diagnosis Prediction under Noisy Clinical Notes with Large Language Models
• TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
• LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection
• SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue
• Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
• RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind
• BAMAS: Structuring Budget-Aware Multi-Agent Systems
• Bayesian Neighborhood Adaptation for Graph Neural Networks
• A Unifying Relational Perspective on Expressive Lottery Tickets
• Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification
• LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
• Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning
• Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
• Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark
• Large Language Model Agents Are Not Always Faithful Self-Evolvers
• Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
• Edge-Assisted Multi-Robot Visual-Inertial SLAM with Efficient Communication
• JoDiffusion: Jointly Diffusing Image with Pixel-Level Annotations for Semantic Segmentation Promotion
• ITPP: Learning Disentangled Event Dynamics in Marked Temporal Point Processes
• Recursive Think-Answer Process for LLMs and VLMs
• 3D-Aware VLMs with Implicit and Explicit Geometries
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
• Evaluation of Vision-LLMs in Surveillance Video
• Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models
• Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression
• ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Driving
• Cross-Cultural Expert-Level Art Critique Evaluation with Vision-Language Models
• Directional Textual Inversion for Personalized Text-to-Image Generation
• Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
• FML-bench: Benchmarking Machine Learning Agents for Scientific Research