AI.info

Latest Research — Page 81

Browse Latest Research on AI.info.

• LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
• Multi-Objective Coevolution of Prompts and Templates for Circuit Approximation
• Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
• Latent Space Factorization in LoRA
• AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling
• Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
• Splatent: Splatting Diffusion Latents for Novel View Synthesis
• "Be My Cheese?": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs
• Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
• LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory
• Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology
• Restoring Pruned Large Language Models via Lost Component Compensation
• Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning
• GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?
• Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
• Topological Signatures of ReLU Neural Network Activation Patterns
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs
• More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
• Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
• Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages
• Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics
• Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
• VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models
• Locally Optimal Private Sampling: Beyond the Global Minimax
• MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
• Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference
• Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images
• OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild
• Abstraction Induces the Brain Alignment of Language and Speech Models
• Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving
• Adaptive Discretization for Consistency Models
• FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
• Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts
• Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
• Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
• CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning
• AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios
• Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning
• Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
• Writing in Symbiosis: Mapping Human Creative Agency in the AI Era