![[2606.02303] Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery](/static/img/curated/desks/afbytes-tech.w400.webp)
[2606.02303] Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery
Abstract page for arXiv paper 2606.02303: Cross-Domain Dead Tree Detection via Knowledge Distillation in Aerial Imagery
![[2606.02302] SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents](/static/img/curated/desks/afbytes-tech.w1200.webp)
[2606.02302] SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
Abstract page for arXiv paper 2606.02302: SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
[2606.02267] A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
Abstract page for arXiv paper 2606.02267: A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
[2606.02268] From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
Abstract page for arXiv paper 2606.02268: From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
[2606.02273] Vision-language Models for Driver Monitoring Systems: A Driver Activity Description Dataset
Abstract page for arXiv paper 2606.02273: Vision-language Models for Driver Monitoring Systems: A Driver Activity Description Dataset
[2606.02274] Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
Abstract page for arXiv paper 2606.02274: Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
[2606.02276] Cross-modal linkage risk in clinical vision-language models
Abstract page for arXiv paper 2606.02276: Cross-modal linkage risk in clinical vision-language models
[2606.02277] RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models
Abstract page for arXiv paper 2606.02277: RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models
[2606.02278] Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Prediction
Abstract page for arXiv paper 2606.02278: Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Prediction
[2606.02280] Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation
Abstract page for arXiv paper 2606.02280: Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptatio...
[2606.02282] POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems
Abstract page for arXiv paper 2606.02282: POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems
[2606.02287] CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation
Abstract page for arXiv paper 2606.02287: CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation
[2606.02357] Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
Abstract page for arXiv paper 2606.02357: Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
[2606.02358] CHIMERA: A Flexible and Scalable 3.1 TOPS/W AI-MCU with Transformer Accelerator and 563 Gb/s Shared-L2 Memory Subsystem with QoS Guarantees
Abstract page for arXiv paper 2606.02358: CHIMERA: A Flexible and Scalable 3.1 TOPS/W AI-MCU with Transformer Accelerator and 563 Gb/s Shared-L2 Memory Subsyste...
[2606.02359] MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
Abstract page for arXiv paper 2606.02359: MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
[2606.02363] Minimax-Optimal Policy Regret in Partially Observable Markov Games
Abstract page for arXiv paper 2606.02363: Minimax-Optimal Policy Regret in Partially Observable Markov Games
[2606.02365] FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
Abstract page for arXiv paper 2606.02365: FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
[2606.02366] PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation
Abstract page for arXiv paper 2606.02366: PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation
[2606.02372] COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Abstract page for arXiv paper 2606.02372: COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
[2606.02434] Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
Abstract page for arXiv paper 2606.02434: Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
[2606.02435] Welfare-Optimal Classification with Accuracy Auctions
Abstract page for arXiv paper 2606.02435: Welfare-Optimal Classification with Accuracy Auctions
[2606.02373] Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Abstract page for arXiv paper 2606.02373: Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
[2606.01436] Learning from Saturated Data: Signals Beyond Correctness for LLM Training
Abstract page for arXiv paper 2606.01436: Learning from Saturated Data: Signals Beyond Correctness for LLM Training
[2606.01437] CEAR: Certified Ensemble Adversarial Robustness in DNNs
Abstract page for arXiv paper 2606.01437: CEAR: Certified Ensemble Adversarial Robustness in DNNs
[2606.01438] Formalizing multi-graded Brenner-Schröer Proj schemes and dilatations of rings in Lean4
Abstract page for arXiv paper 2606.01438: Formalizing multi-graded Brenner-Schröer Proj schemes and dilatations of rings in Lean4
[2606.01440] Understanding Cross-Cloud Interconnects: Hands-On Measurements and Cost Optimization
Abstract page for arXiv paper 2606.01440: Understanding Cross-Cloud Interconnects: Hands-On Measurements and Cost Optimization
[2606.01441] Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
Abstract page for arXiv paper 2606.01441: Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
[2606.01442] On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection
Abstract page for arXiv paper 2606.01442: On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection
[2606.01443] UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
Abstract page for arXiv paper 2606.01443: UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
[2606.01444] Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
Abstract page for arXiv paper 2606.01444: Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
[2606.01450] OpenEye: A Scalable Open-Source Hardware Accelerator for DNNs
Abstract page for arXiv paper 2606.01450: OpenEye: A Scalable Open-Source Hardware Accelerator for DNNs
[2606.01451] Before and After Temperature: A Distributional View of Creative LLM Generation
Abstract page for arXiv paper 2606.01451: Before and After Temperature: A Distributional View of Creative LLM Generation
[2606.01452] NetVAD: Foundation-Model Representation Learning for Identifier-Free Unsupervised Intrusion Detection
Abstract page for arXiv paper 2606.01452: NetVAD: Foundation-Model Representation Learning for Identifier-Free Unsupervised Intrusion Detection
[2606.01456] Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
Abstract page for arXiv paper 2606.01456: Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
[2606.01457] Transferring Information Across Interventions in Causal Bayesian Optimization
Abstract page for arXiv paper 2606.01457: Transferring Information Across Interventions in Causal Bayesian Optimization
[2606.01458] LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
Abstract page for arXiv paper 2606.01458: LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
[2606.01460] A Lightweight Slot-Attention Framework for Multi-Instrument Multi-Pitch Estimation
Abstract page for arXiv paper 2606.01460: A Lightweight Slot-Attention Framework for Multi-Instrument Multi-Pitch Estimation
[2606.01461] Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models
Abstract page for arXiv paper 2606.01461: Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Model...
[2606.01462] An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
Abstract page for arXiv paper 2606.01462: An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
[2606.01464] Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models
Abstract page for arXiv paper 2606.01464: Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models
[2606.01469] Peacemaker at ATE-IT: Automatic term extraction from Italian text for waste management data using encoder model
Abstract page for arXiv paper 2606.01469: Peacemaker at ATE-IT: Automatic term extraction from Italian text for waste management data using encoder model