AI.info
Latest Research — Page 48
Browse Latest Research on AI.info.
- Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage
- When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors
- Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics
- Cross-Primitive Consistency in Jev
- PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer
- GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing
- Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
- Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction
- What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes
- Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance
- Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice
- HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks
- CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark
- Structure Detection for Contextual Reinforcement Learning
- SOSControl: Enhancing Human Motion Generation through Saliency-Aware Symbolic Orientation and Timing Control
- Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers
- Symbol-Equivariant Recurrent Reasoning Models
- Revisiting Node Affinity Prediction in Temporal Graphs
- LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
- Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs
- A Diffusive Classification Loss for Learning Energy-based Generative Models
- Spectral-Spatial Interpretation
- ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groups
- To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation
- Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
- ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration
- Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
- Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
- Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of Low-Level Pretrained Diffusion Features
- Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers
- Lossless Vocabulary Reduction for Auto-Regressive Language Models
- NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
- HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data
- FineXtrol: Controllable Motion Generation via Fine-Grained Text
- From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Management
- Know Thyself by Knowing Others: Learning Neuron Identity from Population Context
- A logical re-conception of neural networks: Hamiltonian bitwise part-whole architecture
- Consensus Group Relative Policy Optimization for Text Generation
- Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing
- Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG