AI.info

Latest Research — Page 94

Browse Latest Research on AI.info.

• Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
• KV Cache Transform Coding for Compact Storage in LLM Inference
• Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages
• Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence
• RARE: Decoupling Representation Steering from Expert Routing in Mixture-of-Experts Language Models
• ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Dataset
• Testing Most Influential Sets
• The Underappreciated Power of Vision Models for Graph Structural Understanding
• Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics
• EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
• MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
• Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
• TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
• VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
• Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
• Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints
• Moral Sycophancy in Vision Language Models
• Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams
• Improving ML Training Data with Gold-Standard Quality Metrics
• Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models
• Multi-Distribution Robust Conformal Prediction
• Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
• Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
• Error-Driven Scene Editing for 3D Grounding in Large Language Models
• Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting
• AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs
• MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation
• A Platform for Interactive AI Character Experiences
• A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits
• The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
• Appearing Legitimate is Not Enough: Interrogating Synthetic Agents in Representational Processes through a Participatory Design Lens
• Moral Hazard in Multi-Agent Language Models
• Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication
• DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
• Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
• Classifier-Augmented Generation for Structured Workflow Prediction
• GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models
• Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments
• A Model of Causal Explanation on Neural Networks for Tabular Data