AI.info

Latest Research — Page 99

Browse Latest Research on AI.info.

• Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images
• Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
• Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
• InfMem: Learning System-2 Memory Control for Long-Context Agent
• The Realignment Problem: When Right becomes Wrong in LLMs
• Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
• Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
• PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis
• Voxify3D: Pixel Art Meets Volumetric Rendering
• Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis
• EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMs
• SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
• ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue
• How Patterns Dictate Learnability in Sequential Data
• OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
• When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
• String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
• Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
• Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos
• Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
• Thermo-responsive closing and reopening artificial Venus Flytrap utilizing shape memory elastomers
• Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
• Training-Trajectory-Aware Token Selection
• Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition
• Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Representation in the Hansard Corpus
• Reasoning with Pixel-level Precision: QVLM Architecture and SQuID Dataset for Quantitative Geospatial Analytics
• UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems
• Using Salient Object Detection to Identify Manipulative Cookie Banners that Circumvent GDPR
• Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards
• Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
• Rethinking PCA Through Duality
• See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
• OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
• Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs
• It's all In the (Exponential) Family: An Equivalence between Maximum Likelihood Estimation and Control Variates for Sketching Algorithms
• HistoPrism: Unlocking Functional Pathway Analysis from Pan-Cancer Histology via Gene Expression Prediction
• When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF
• A Benchmark for Deep Information Synthesis
• EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue
• Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers