AI.info
Latest Research — Page 55
Browse Latest Research on AI.info.
- CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
- SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making
- Generative Late-Interaction Embeddings For Visual Document Retrieval
- Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception
- Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws
- VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning
- DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
- Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoning
- Twin Restricted Kernel Machines for Multiview Classification
- Multi-Perspective Subimage CLIP with Keyword Guidance for Remote Sensing Image-Text Retrieval
- Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion
- From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
- Language Models Entangle Language and Culture
- EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
- VideoMemBench: How Well Do MLLMs Remember in Video Conversations?
- D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models
- TransientTrack: Advanced Multi-Object Tracking and Classification of Cancer Cells with Transient Fluorescent Signals
- Improving Flow Matching by Aligning Flow Divergence
- Kinship Data Benchmark for Multi-hop Reasoning
- Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations
- SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design
- MoDora: Tree-Based Semi-Structured Document Analysis System
- AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
- Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
- Diffusion Guided Adversarial State Perturbations in Reinforcement Learning
- FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fiction
- GenCP: Towards Generative Modeling Paradigm of Coupled Physics
- Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
- Learning Correlated Reward Models: Statistical Barriers and Opportunities
- DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes
- Online Learning with LLM Experts from Limited Feedback
- Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model
- Compensating Distribution Drifts in Class-incremental Learning of Pre-trained Vision Transformers
- Spatiotemporal Wildfire Prediction and Reinforcement Learning for Helitack Suppression
- Pisets: A Robust Speech Recognition System for Lectures and Interviews
- Search Self-play: Pushing the Frontier of Agent Capability without Supervision
- Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive Benchmarks
- Knowledge-Guided Multimodal Reasoning over Interacting Streams for Video-Level Ambivalence and Hesitancy Recognition
- A Graph-based RAG for Energy Efficiency Question Answering