AI.info

Latest Research — Page 12

Browse Latest Research on AI.info.

• White-Box Sensitivity Auditing with Steering Vectors
• TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction
• Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
• KLASS: KL-Guided Fast Inference in Masked Diffusion Models
• How to Correctly Report LLM-as-a-Judge Evaluations
• Bridging Tool Dependencies and Domain Knowledge: A Graph-Based Framework for In-Context Planning
• RIFT: Reordered Instruction Following Testbed To Evaluate Instruction Following in Singular Multistep Prompt Structures
• Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
• Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata
• DTBench: A Synthetic Benchmark for Document-to-Table Extraction
• LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight
• Memory-Centric Continual Learning for AI Agents
• HybriDLA: Hybrid Generation for Document Layout Analysis
• Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving
• Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents
• Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering
• VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors
• Robustness of Structured Data Extraction from Perspectively Distorted Documents
• Structured Personalization: Modeling Constraints as Matroids for Data-Minimal LLM Agents
• MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation
• ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation
• Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal Prostate MRI Segmentation
• Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
• SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration
• One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
• Chain-of-Thought Oversight Requires Separate Evidence for Faithfulness and Monitorability
• AgentKernel: The Trust-Native Agentic Operating System
• StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
• Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
• RoboJEPA: Scaling Robotic Latent World Models
• RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems
• A Reliable Indoor Navigation System for Humans Using AR-based Technique
• MAMA-Memeia! Multi-Aspect Multi-Agent Collaboration for Depressive Symptoms Identification in Memes
• MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation
• Group and Exclusive Sparse Regularization-based Continual Learning of CNNs
• TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training
• CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems
• AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory
• Gender Bias in Emotion Recognition by Large Language Models