AI.info

Latest Research — Page 71

Browse Latest Research on AI.info.

• MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions
• Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
• PCoA: A New Benchmark for Medical Aspect-Based Summarization With Phrase-Level Context Attribution
• DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
• Judge Reliability Harness: Stress Testing the Reliability of LLM Judges
• Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
• OffNadirLoc: Benchmark and Framework for Challenging UAV-to-Satellite Geo-Localization under Large Off-Nadir Views
• Optimal Self-Consistency for Efficient Reasoning with Large Language Models
• Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data
• Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ
• Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
• Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
• A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
• Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion
• Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
• NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment
• I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks
• Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
• Seeing Red, Thinking Bad: Color Bias in Vision Language Models
• No Pixel Left Behind: Filling Gaps in Anime Colorization
• Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
• GISA: A Benchmark for General Information-Seeking Assistant
• Order Matters: 3D Shape Generation from Sequential VR Sketches
• Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games
• VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking
• From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition
• TempCloze: Can Video-LLMs Identify the Missing Middle?
• RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
• SiMiC: Context-Aware Silicon Microstructure Characterization Using Attention-Based Convolutional Neural Networks for Field-Emission Tip Analysis
• Weak-to-Strong Generalization under Distribution Shifts
• Boosting Adversarial Transferability via Ensemble Non-Attention
• Differential syntactic and semantic encoding in LLMs
• AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning
• Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages
• PlantTraitNet: An Uncertainty-Aware Multimodal Framework for Global-Scale Plant Trait Inference from Citizen Science Data
• Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
• Near--Real-Time Conflict-Related Fire Detection in Sudan Using Unsupervised Deep Learning
• Plug-and-Play Parameter-Efficient Tuning of Embeddings for Federated Recommendation
• Bridging Embodiment Gaps: Deploying Vision-Language-Action Models on Soft Robots
• Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models