![[2605.31162] Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models](/static/img/curated/desks/afbytes-tech.w400.webp)
[2605.31162] Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
Abstract page for arXiv paper 2605.31162: Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
![[2605.31158] Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models](/static/img/curated/desks/afbytes-tech.w1200.webp)
[2605.31158] Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
Abstract page for arXiv paper 2605.31158: Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
[2605.31174] Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning
Abstract page for arXiv paper 2605.31174: Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning
[2605.31175] Towards Efficient LLMs Annealing with Principled Sample Selection
Abstract page for arXiv paper 2605.31175: Towards Efficient LLMs Annealing with Principled Sample Selection
[2605.31177] Vanilla ViT for Automotive Point Cloud Semantic Segmentation
Abstract page for arXiv paper 2605.31177: Vanilla ViT for Automotive Point Cloud Semantic Segmentation
[2605.31186] How well does Classification Accuracy capture Concept Drift Detection Quality? An overview of Concept Drift Detection evaluation
Abstract page for arXiv paper 2605.31186: How well does Classification Accuracy capture Concept Drift Detection Quality? An overview of Concept Drift Detection ...
[2605.31187] From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
Abstract page for arXiv paper 2605.31187: From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
[2605.30621] Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
Abstract page for arXiv paper 2605.30621: Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
[2605.30637] EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs
Abstract page for arXiv paper 2605.30637: EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs
[2605.30664] Structure-Induced Information for Rerooting Levin Tree Search
Abstract page for arXiv paper 2605.30664: Structure-Induced Information for Rerooting Levin Tree Search
[2605.30680] Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
Abstract page for arXiv paper 2605.30680: Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
[2605.30738] MAVEN: Improving Generalization in Agentic Tool Calling
Abstract page for arXiv paper 2605.30738: MAVEN: Improving Generalization in Agentic Tool Calling
[2605.30747] Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models
Abstract page for arXiv paper 2605.30747: Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models
[2605.30785] Learning Agent-Compatible Context Management for Long-Horizon Tasks
Abstract page for arXiv paper 2605.30785: Learning Agent-Compatible Context Management for Long-Horizon Tasks
[2605.30803] PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
Abstract page for arXiv paper 2605.30803: PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
[2605.30824] Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward
Abstract page for arXiv paper 2605.30824: Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward
[2605.30832] SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
Abstract page for arXiv paper 2605.30832: SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
[2605.30838] COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
Abstract page for arXiv paper 2605.30838: COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
[2605.30861] Distilling LLM Feedback for Lean Theorem Proving
Abstract page for arXiv paper 2605.30861: Distilling LLM Feedback for Lean Theorem Proving
[2605.30898] UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling
Abstract page for arXiv paper 2605.30898: UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling
[2605.31021] A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI
Abstract page for arXiv paper 2605.31021: A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI
[2605.31023] HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster
Abstract page for arXiv paper 2605.31023: HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster
[2605.31031] GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
Abstract page for arXiv paper 2605.31031: GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
[2605.31100] Vector Linking via Cross-Model Local Isometric Consistency
Abstract page for arXiv paper 2605.31100: Vector Linking via Cross-Model Local Isometric Consistency
[2605.31167] LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
Abstract page for arXiv paper 2605.31167: LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
[2605.31254] Formalizing and falsifying causal pathways of rare events
Abstract page for arXiv paper 2605.31254: Formalizing and falsifying causal pathways of rare events
[2605.31264] COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Abstract page for arXiv paper 2605.31264: COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
[2404.14928] Graph Machine Learning in the Era of Large Language Models (LLMs)
Abstract page for arXiv paper 2404.14928: Graph Machine Learning in the Era of Large Language Models (LLMs)
[2411.13865] Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems
Abstract page for arXiv paper 2411.13865: Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems
[2411.19463] Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems
Abstract page for arXiv paper 2411.19463: Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems
[2501.01926] Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
Abstract page for arXiv paper 2501.01926: Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
[2501.04661] Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
Abstract page for arXiv paper 2501.04661: Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
[2502.12119] PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Abstract page for arXiv paper 2502.12119: PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
[2502.15224] Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery
Abstract page for arXiv paper 2502.15224: Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery
[2503.05846] EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
Abstract page for arXiv paper 2503.05846: EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multili...
[2505.22934] Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
Abstract page for arXiv paper 2505.22934: Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
[2506.08255] SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Abstract page for arXiv paper 2506.08255: SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
[2605.30561] VLM3: Vision Language Models Are Native 3D Learners
Abstract page for arXiv paper 2605.30561: VLM3: Vision Language Models Are Native 3D Learners
[2605.30581] Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes
Abstract page for arXiv paper 2605.30581: Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes
[2605.30585] Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation
Abstract page for arXiv paper 2605.30585: Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradat...
[2605.30589] ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
Abstract page for arXiv paper 2605.30589: ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
[2605.30590] Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents
Abstract page for arXiv paper 2605.30590: Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents
[2605.30593] Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction
Abstract page for arXiv paper 2605.30593: Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction
[2605.30604] An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations
Abstract page for arXiv paper 2605.30604: An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations
[2605.30611] Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Abstract page for arXiv paper 2605.30611: Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
[2605.30628] The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
Abstract page for arXiv paper 2605.30628: The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
[2605.30381] When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
Abstract page for arXiv paper 2605.30381: When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
[2605.30675] Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
Abstract page for arXiv paper 2605.30675: Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
[2605.30677] Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
Abstract page for arXiv paper 2605.30677: Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents