AI.info

Latest Research — Page 68

Browse Latest Research on AI.info.

• Face De-Identification: A Domain-Centric Survey from Capture to Processing
• The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning
• Physics-Informed Large Language Models for HVAC Anomaly Detection with Autonomous Rule Generation
• Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
• RePo: Language Models with Context Re-Positioning
• Conserved Immune Topology Improves Pathology Foundation Model Generalization for Cross-Cancer MSI-H Prediction
• ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction
• Stay Within Your Bounds: Distance-Guided Decoding for Guaranteed Context-Free Grammar Compliance
• SoulAuth: An Actor-native Identity Architecture and Rust Reference Implementation for Humans and Long-lived AI Actors
• Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
• ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models
• ReferTrack: Referring Then Tracking for Embodied Visual Tracking
• G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition
• Grounding latent algorithm routing in transformer reasoning
• Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge
• V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs
• BertsWin: Resolving Topological Sparsity in 3D Masked Autoencoders via Component-Balanced Structural Optimization
• LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It
• A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models
• You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering
• Enhancing Spatial Understanding in Image Generation via Reward Modeling
• ChartComplete: A Taxonomy-based Inclusive Chart Dataset
• The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits
• Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression
• LASER: An LLM-based ASR Scoring and Evaluation Rubric
• Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
• Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
• Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model
• Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs
• First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves
• NAAMSE: Framework for Evolutionary Security Evaluation of Agents
• DIMO: Diverse 3D Motion Generation for Arbitrary Objects
• Prototype Transformer: Towards Language Model Architectures Interpretable by Design
• Deep Learning-Based Estimation of Ground Reaction Forces in Parkinsonian Gait Using an Optimized Set of IMU Data
• SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction
• Inverse Depth Scaling From Most Layers Being Similar
• Abductive Reasoning with Syllogistic Forms in Large Language Models
• OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting
• Navigating Simply, Aligning Deeply: Winning Solutions for Mouse vs. AI 2025
• Valeo Near-Field: a novel dataset for pedestrian intent detection