AI.info

Latest Research — Page 39

Browse Latest Research on AI.info.

• Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries
• ST-Raptor: An Agentic System for Semi-Structured Table QA
• GIR-Bench: Versatile Benchmark for Generating Images with Reasoning
• Emergent Persuasion: Will LLMs Persuade Without Being Prompted?
• Protein Circuit Tracing via Cross-layer Transcoders
• Class-Partitioned VQ-VAE and Latent Flow Matching for Point Cloud Scene Generation
• SlicerOrbitSurgerySim: An Open-Source Platform for Virtual Registration and Quantitative Comparison of Preformed Orbital Plates
• RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-Agent
• FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion
• Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
• ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
• OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
• INR-Bench: A Unified Benchmark for Implicit Neural Representations in Multi-Domain Regression and Reconstruction
• Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
• Less from More: Reinforcing Sparse Video Reasoning from Dense References
• BrickWright: Agentic Creation of Physically Feasible Brick Builds
• Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?
• SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly
• AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation
• LLHA-Net: A Hierarchical Attention Network for Two-View Correspondence Learning
• Revisiting Multi-Task Visual Representation Learning
• HuatuoGPT-3: RL-Only Domain Adaptation from Base Models
• Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning
• G2: Guided Generation for Enhanced Output Diversity in LLMs
• Two-Step Occupation Coding
• SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking
• Mixed Data Clustering Survey and Challenges
• X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
• Decision-Oriented Recommendation Reranking: An Empirical Study of Jev
• GeoDynamics: A Geometric State-Space Neural Network for Understanding Brain Dynamics on Riemannian Manifolds
• Learning from Synthetic Data Improves Multi-hop Reasoning
• JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
• Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory
• Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
• LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
• Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
• Decentralized Multi-Agent Swarms for Autonomous Grid Security in Industrial IoT: A Consensus-based Approach
• Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
• Data Heterogeneity and Forgotten Labels in Split Federated Learning
• Understanding Clustering in Slot Attention via Particle Dynamics