AI.info
Latest Research — Page 46
Browse Latest Research on AI.info.
- Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks
- VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing
- World Model Interpretability: From Decoding Representations to Understanding Latent Worlds
- CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing
- Global Sensitivity Analysis for Engineering Design Based on Individual Conditional Expectations
- Socio-cognitive agent-oriented evolutionary algorithm with trust-based optimization
- recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models
- MedBioRAG: Semantic Search and Retrieval-Augmented Generation with Large Language Models for Medical and Biological QA
- ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
- MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents
- TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
- CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting
- Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models
- SoK: Semantic Decision Engines in Network Control Loops
- Reward Modeling from Natural Language Human Feedback
- Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation
- Silenced Biases: The Dark Side LLMs Learned to Refuse
- PVBench: Quantifying Physical Plausibility in Video Generation with Object-Level Physical Measurements
- PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
- Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
- The Map of Misbelief: Tracing Intrinsic and Extrinsic Hallucinations Through Attention Patterns
- Pristine Models
- Touching Emotions, Smelling Shapes: Exploring Tactile, Olfactory and Emotional Cross-sensory Correspondences in Preschool Aged Children
- LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation
- TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation
- Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Video
- EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
- A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation
- Car Drag Coefficient Prediction from 3D Point Clouds Using a Slice-Based Surrogate Model
- MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities
- MolLean: A Process-Verifiable Language for Chemical Reasoning
- Reward-free Alignment for Conflicting Objectives
- TopoBench: Benchmarking LLMs on Hard Topological Reasoning
- Lark: Biologically Inspired Neuroevolution for Multi-Stakeholder LLM Agents
- GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search
- Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks
- E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges
- Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
- GOATex: Geometry & Occlusion-Aware Texturing
- Can QE-informed (Re)Translation lead to Error Correction?