AI.info
Latest Research — Page 86
Browse Latest Research on AI.info.
- Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
- STAMP: Spatial-Temporal Adapter with Multi-Head Pooling
- Action-Free Offline-to-Online RL via Discretised State Policies
- Time-Optimal Transport of Loosely Placed Liquid Filled Cups along Prescribed Paths
- Laplacian Representations for Decision-Time Planning
- AnyPcc: Compressing Any Point Cloud with a Single Universal Model
- GANDR: Claim Auditing for Verifiable Legal Answer Generation
- A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization
- Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
- Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
- MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
- Sensus Pond: Exploring Water as Sensing Medium for More-than-Human Observation
- MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning
- MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
- TangledFeatures: Robust Feature Selection in Highly Correlated Spaces
- Intrinsic Dimension Estimation for Radio Galaxy Zoo using Diffusion Models
- MorphoOrgaAgent: A Foundation-Model-Based Multi-Agent System for Autonomous Organoid Analysis
- From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement
- Programming over Thinking: Efficient and Robust Multi-Constraint Planning
- PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion
- MAxBench: A Multinomial Concept Recovery Benchmark
- Financial Instruction Following Evaluation (FIFE)
- PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
- RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
- ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
- The Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation
- Expert Merging in Sparse Mixture of Experts with Nash Bargaining
- One note in three: a verified census of three deployed AI scribes, and the instrument that counted it
- From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
- FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
- SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away
- GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
- CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas
- MMhops-R1: Multimodal Multi-hop Reasoning
- CountGD++: Generalized Prompting for Open-World Counting
- Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation
- BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
- Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs
- AutoPR: Let's Automate Your Academic Promotion!
- Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency