AI.info

Latest Research — Page 19

Browse Latest Research on AI.info.

• MILD: Tractable Terrain Modeling for Learning Improved Bipedal Locomotion on Deformable Surfaces
• Compact Example-Based Explanations for Language Models
• BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
• Sparse Methods for Vector Embeddings of TPC Data
• Capturing Head Avatar with Hand Contacts from a Monocular Video
• Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations
• From Observations to Events: Event-Aware World Model for Reinforcement Learning
• Interpreting the Latent Structure of Operator Precedence in Language Models
• Improving Day-Ahead Grid Carbon Intensity Forecasting by Joint Modeling of Local-Temporal and Cross-Variable Dependencies Across Different Frequencies
• Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems
• Ask a Strong LLM Judge when Your Reward Model is Uncertain
• CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification
• Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
• Exploring Landscapes for Better Minima along Valleys
• ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
• Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understanding
• Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
• Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences
• CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop
• Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models
• Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
• HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
• CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization
• ABLE: Using Adversarial Pairs to Construct Local Models for Explaining Model Predictions
• Cooperative Pseudo Labeling for Unsupervised Federated Classification
• MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness
• Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers
• Protein Counterfactuals via Diffusion-Guided Latent Optimization
• Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
• DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation
• UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
• Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
• OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning
• Adaptive Multi-Agent Response Refinement in Conversational Systems
• LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
• [Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games
• Cyclic Counterfactuals under Shift-Scale Interventions
• Your Language Model Secretly Contains Personality Subnetworks
• OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
• OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion