AI.info

Latest Research — Page 129

Browse Latest Research on AI.info.

• Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
• Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
• Designing Incident Reporting Systems for Harms from General-Purpose AI
• Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search
• WhAM: Towards A Translative Model of Sperm Whale Vocalization
• Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models
• Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
• Membership and Dataset Inference Attacks on Large Audio Generative Models
• MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
• The Path Not Taken: RLVR Provably Learns Off the Principals
• Do Flat Minima Improve Sparse Novel View Synthesis?
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
• TOSSS: a CVE-based Software Security Benchmark for Large Language Models
• Hierarchical Semantic Alignment for Image Clustering
• ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy
• GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
• PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
• Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
• HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering
• UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models
• Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs
• Graph4MM: Weaving Multimodal Learning with Structural Information
• DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
• E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimation
• MMMamba: A Versatile Cross-Modal In Context Fusion Framework for Pan-Sharpening and Zero-Shot Image Enhancement
• PRMU: A Corpus-Free Benchmark for Person-Centric Knowledge Unlearning in Multimodal Large Language Models
• FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding
• An approach for combining transparency and motion assistance of a lower body exoskeleton
• TEFormer: Structured Bidirectional Temporal Enhancement Modeling in Spiking Transformers
• GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
• EvReflection: Event-Driven Micro-Dynamics for Reflection Removal
• SDSR: A Spectral Divide-and-Conquer Approach for Species Tree Reconstruction
• Scaling Unsupervised Word Alignment to Documents via Structural Constraints
• GraphIF: Enhancing Multi-Turn Instruction Following for Large Language Models with Relation Graph Prompt
• Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
• SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
• COMI: Coarse-to-fine Context Compression via Marginal Information Gain
• CitiLink: Enhancing Municipal Transparency and Citizen Engagement through Searchable Meeting Minutes
• IR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensing
• ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems