AI.info

Latest Research — Page 58

Browse Latest Research on AI.info.

• Modality Matching Matters: Calibrating Language Distances for Cross-Lingual Transfer in URIEL+
• PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
• Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
• Counterfactual Identifiability via Dynamic Optimal Transport
• DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models
• ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support
• PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
• Structure-based RNA Design by Step-wise Optimization of Latent Diffusion Model
• RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models
• Preference-driven Knowledge Distillation for Few-shot Node Classification
• Spatiotemporal Pyramid Flow Matching for Climate Emulation
• Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
• Step-by-step Layered Design Generation
• Single-Beat Cuffless Blood Pressure Estimation Using Ear-PPG and ECG with a Lightweight Hybrid Learning Framework
• DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
• Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
• Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks
• Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs
• MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
• Relaxation-Aware Multimodal Sensing of Soft Gripper Driven by Structure-Perception-Learning
• Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
• Guiding a Diffusion Transformer with the Internal Dynamics of Itself
• GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation
• Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences
• Local Causal Discovery for Statistically Efficient Causal Inference
• Multimodal Fact-Level Attribution for Verifiable Reasoning
• Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions
• Optimistic Task Inference for Behavior Foundation Models
• Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis
• Extending Audio Context for Long-Form Understanding in Large Audio-Language Models
• AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
• DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation
• Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server
• EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications
• Capacity Constraints Make Admissions Processes Less Predictable
• Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
• Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales
• IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning
• AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
• EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval