AI.info

Latest Research — Page 26

Browse Latest Research on AI.info.

• Are Language Models Efficient Reasoners? A Perspective from Logic Programming
• BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
• Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
• Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
• Predicting the Unpredictable: Reproducible BiLSTM Forecasting of Incident Counts in the Global Terrorism Database (GTD)
• IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation
• MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenes
• DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections
• Multiplicative Orthogonal Sequential Editing for Language Models
• Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
• ReIn: Conversational Error Recovery with Reasoning Inception
• TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size
• SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
• RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
• UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders
• PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
• How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models
• Exploring the Heterogeneity of Tabular Data: A Diversity-aware Data Generator via LLMs
• Grounding and Enhancing Informativeness and Utility in Dataset Distillation
• CHUG: Crowdsourced User-Generated HDR Video Quality Dataset
• S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
• AnyThermal: Towards Learning Universal Representations for Thermal Perception
• MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model
• On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering
• Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering
• Echoing: Identity Failures when LLM Agents Talk to Each Other
• HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application
• LTEM: LLM-Friendly Table-Enhanced Markdown for Table Understanding and Generation
• Perch 2.0 transfers 'whale' to underwater tasks
• From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language Models
• Forecasting in Offline Reinforcement Learning for Non-stationary Environments
• Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding
• Uniform Discrete Diffusion with Metric Path for Video Generation
• Small Foundation Models of Human Cognition and Behaviour
• DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems
• EditaLive! Unified Character Video Editing for Live Streaming
• MeanFlow Transformers with Representation Autoencoders
• Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions
• Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation
• BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards