AI.info

Latest Research — Page 70

Browse Latest Research on AI.info.

• Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
• WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
• When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers
• FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation
• Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms
• Prescriptive Artificial Intelligence: A Formal Paradigm for Auditing Human Decisions Under Uncertainty
• H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation
• EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
• CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency
• MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
• Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
• Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI Agents
• An Invariant Latent Space Perspective on Language Model Inversion
• Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation
• Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
• CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
• HealSplit: Towards Self-Healing through Adversarial Distillation in Split Federated Learning
• Reconstructing Humans and Objects in Interaction using Large Reconstruction Models
• BOP-ASK: Object-Interaction Reasoning for Vision-Language Models
• Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing
• GAMBIT+: A Challenge Set for Evaluating Gender Bias in Machine Translation Quality Estimation Metrics
• Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation
• DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning
• NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code
• Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry
• Can Large Language Models Differentiate Harmful from Argumentative Essays? Steps Toward Ethical Essay Scoring
• A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
• Towards One-step Causal Video Generation via Adversarial Self-Distillation
• Krause Synchronization Transformers
• Subspace Inference Enables Efficient Active Reward Learning from Preferences
• SSMB: Self-Supervised Local Feature Detection under Motion Blur
• PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
• REMem: Reasoning with Episodic Memory in Language Agent
• FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
• CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
• An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
• Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
• CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model
• DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis