AI.info
Latest Research — Page 22
Browse Latest Research on AI.info.
- HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks
- BankMathBench: A Benchmark for Numerical Reasoning in Banking Scenarios
- Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology
- Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
- PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization
- Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment
- Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps
- Vision-aligned Latent Reasoning for Multi-modal Large Language Model
- Inferential Question Answering
- Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP
- NNGPT: Rethinking AutoML with Large Language Models
- EEG-D3: A Solution to the Hidden Overfitting Problem of Deep Learning Models
- AutoEnvScaling: Automating the Data Flywheel with Terminal Agents
- Learning $ω$-Powered Conditional Distributions with Importance-Weighted Flow Matching
- A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection
- Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction
- VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
- U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching
- Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning
- Large-FOV RGBD Imaging via Structured PSF Coding in a Bio-inspired Monocentric System
- A New Dataset and Framework for Robust Road Surface Classification via Camera-IMU Fusion
- GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
- Vehicle Routing with Finite Time Horizon using Deep Reinforcement Learning with Improved Network Embedding
- Reasoning is a Modality
- X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
- Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
- Self-Explaining Hate Speech Detection with Moral Rationales
- A Mixed Diet Makes DINO An Omnivorous Vision Encoder
- C3: Speech-Guided KV Retrieval for Long-Context SpeechLLM Inference
- InnoText: A Unified Model for Visual Text Generation and Editing
- VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
- Learning Self-Orchestration in Decentralized Agent Swarms
- Bridging the gap: A comparative exploration of Speech-LLM and end-to-end architecture for multilingual conversational ASR
- What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
- Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation
- Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones
- R3ST: A Synthetic 3D Dataset With Realistic Trajectories
- Confounding Robust Deep Reinforcement Learning: A Causal Approach
- AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
- Optimization and Mobile Deployment for Anthropocene Neural Style Transfer