AI.info

Latest Research — Page 106

Browse Latest Research on AI.info.

• RS-ORT: A Reduced-Space Branch-and-Bound Algorithm for Optimal Regression Trees
• SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion
• Space Explanations of Neural Network Classification
• Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
• RIPCN: A Road Impedance Principal Component Network for Probabilistic Traffic Flow Forecasting
• Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
• LLM Unlearning with LLM Beliefs
• ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
• LongCat-DeepResearch Technical Report
• Enhancing Financial Literacy and Management through Goal-Directed Design and Gamification in Personal Finance Application
• STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
• Geometry Matters in Packed 3D Attention
• Building Interpretable Models for Moral Decision-Making
• Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
• Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning
• Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
• K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
• Scaling Unsupervised Multi-Source Federated Domain Adaptation through Group-Wise Discrepancy Minimization
• The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
• From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
• Rethinking Projector Training in Multimodal LLMs
• ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body
• Small Language Models as Judges for Rubric-Based Reinforcement Learning
• Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation
• SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
• Schrödinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics
• Beyond Fixed Psychological Personas: State Beats Trait, but Language Models are State-Blind
• Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
• Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
• Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
• OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination
• Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking
• Irresponsible AI: big tech's influence on AI research and associated impacts
• Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy
• ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search
• Modular AI-Powered Interviewer with Dynamic Question Generation and Expertise Profiling
• Frequency Regularization: Unveiling the Spectral Inductive Bias of Deep Neural Networks
• Uni-Animator: Towards Unified Visual Colorization
• MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
• What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics