INDEX
Every paper Pith has read and judged, in one searchable index.
-
cs.CV arXiv submitted 2026-08-03First real-time diffusion video relighting hits 15.78 fps
Yue Ma +10 · “LiveLight: Real-time Streaming Video Relighting with Interactive Control”
2608.01771 -
cs.AI arXiv submitted 2026-08-03AI-guided food inspections beat manual plan: 11% vs 9%
Dongqi Wang +3 · “Leveraging AI for fine-grained food safety risk forecasting in sparse data conditions”
2608.01767 -
cs.CR arXiv submitted 2026-08-03Logic check lifts verified LLM paths from 78% to 98%
Kaustuv Mukherji +6 · “EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming”
2608.01763 -
cs.CV arXiv submitted 2026-08-03Decoupled 3DGS renders interactive driving sims at 45 FPS
Siying Li +4 · “DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing”
2608.01761 -
cs.CV arXiv submitted 2026-08-03Superpixel-guided scanning restores weather-degraded images to 34.15 dB
Dayu Li +5 · “Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM”
2608.01760 -
cs.CR arXiv submitted 2026-08-03Harmless tasks add up to an 86% attack success on self-evolving agents
Bingyu Yan +5 · “Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents”
2608.01759 -
cs.CV arXiv submitted 2026-08-03Stacking three AI vision models lifts blight detection over any single model
Xiaohao Yang +4 · “Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit”
2608.01753 -
cs.CV arXiv submitted 2026-08-03All-band router lifts satellite segmentation accuracy 2.9 points
Xingyan Li +4 · “SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models”
2608.01751 -
cs.GR arXiv submitted 2026-08-03Ptychography can drop strict linearity and gain resolution
Yun Xie +4 · “High-fidelity tabletop nanoscopy enabled by non-linear spectral preconditioning”
2608.01746 -
cs.LG arXiv submitted 2026-08-03Virtual queues pace network budgets inside every episode
Yeonseo Jeong +3 · “Heterogeneous Multi-Agent Reinforcement Learning for Radio Resource Management under Coupled Finite-Horizon Constraints”
2608.01745 -
cs.AI arXiv submitted 2026-08-03RL finds interlocking assemblies where heuristic search stalls
Xuyang Ma +5 · “RL-Lock: Reinforcement Learning for Generating Interlocking Assemblies”
2608.01744 -
cs.LG arXiv submitted 2026-08-03KL regularizer that ignores wrong answers stops LLM forgetting
Li Wang +6 · “Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning”
2608.01743 -
cs.AI arXiv submitted 2026-08-03Dual-track memory lifts LLM agent QA accuracy by up to 8.8%
Yufei Luo +2 · “MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents”
2608.01742 -
cs.LG arXiv submitted 2026-08-03Two forecasts' disagreement speeds up diffusion sampling
Yanchao Li +8 · “Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts”
2608.01740 -
cs.RO arXiv submitted 2026-08-03Drone that grips its target holds still within 3 mm
Joshua Taylor +4 · “A Tilt-Rotor UAV with a Gripper for Stable Contact-Based Tasks via Environmental Anchoring”
2608.01736 -
cs.AI arXiv submitted 2026-08-03Cut privilege illusion
Jianyu Wu +4 · “DAPD: Dual-Anchored Policy Distillation”
2608.01735 -
cs.LG arXiv submitted 2026-08-03LLM-chosen drug neighbors top complex baselines in cell-line tests
Betty Xiong +4 · “LLM-Guided Retrieval for Prediction of Molecular Perturbation Responses”
2608.01734 -
cs.RO arXiv submitted 2026-08-03Robots learn to use arms and chest from a wearable twin
Takahide Kitamura +3 · “TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning”
2608.01733 -
cs.IR arXiv submitted 2026-08-03Graph-grounded LLM explanations beat popularity ranking by 17.1%
Meenakshi Rajpurohit +1 · “X-KGRank: A Knowledge Graph RAG Framework for Explainable Recommendations via Pattern Mining and LLM Re-Ranking”
2608.01732 -
cs.IR arXiv submitted 2026-08-03Repeated best responses make recommendation lists mutually optimal
Yoji Tomita · “MODE: Mutual Optimality in Direct Effects of Reciprocal Recommendations in Matching Markets”
2608.01731 -
cs.CV arXiv submitted 2026-08-03Image-quality model tops benchmarks at every resolution
Hakan Emre Gedik +2 · “Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency”
2608.01730 -
cs.NI arXiv submitted 2026-08-03Ten-factor score reorders CVSS in a synthetic SD-WAN test
Saeed Alam · “Predictive Exposure and Cryptographic Readiness: A Vendor-Neutral Framework, a, Bounded Multivocal Evidence Analysis, and Reproducible Synthetic Evaluation for SD-WAN Environments”
2608.01728 -
cs.CV arXiv submitted 2026-08-03Rig 3D Gaussians with no rigging data via diffusion priors
Yuxin Yao +4 · “G-Skin: Learning to Bind 3D Gaussians with Generative Visual Priors”
2608.01726 -
cs.NI arXiv submitted 2026-08-03One telemetry model cuts HPC slowdown by up to 77%
Zifan Zhang +3 · “CENTILE: A Telemetry Foundation Model Evaluated by the Decisions It Drives”
2608.01725 -
cs.CL arXiv submitted 2026-08-03Semester-long team recordings lift next-speaker prediction 13.8 points
Heechan Lee +5 · “TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics”
2608.01724 -
cs.CV arXiv submitted 2026-08-03One-step latent flow beats dark RAW motion-blur rivals by 7.42 dB
Zepu Wang +3 · “When Extreme Darkness Meets Motion Blur: MeanFlow for Unified RAW Restoration”
2608.01720 -
cs.CR arXiv submitted 2026-08-03Scoped disclosures cut agent leakage to 0.035
Jinghan Xu +4 · “MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication”
2608.01719 -
cs.AI arXiv submitted 2026-08-03Lookahead check stops LLM cache-poisoning attacks
Jiacheng Liang +3 · “LaCache: Robust Semantic Caching for LLM Serving”
2608.01718 -
cs.LG arXiv submitted 2026-08-03External rollouts train diffusion language models to 98.4% on Sudoku
Wonseok Lee +3 · “Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models”
2608.01717 -
cs.SE arXiv submitted 2026-08-03Agent-built tests expose 589 bugs official AtCoder suites miss
Shuyang Xie +4 · “Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch”
2608.01715 -
cs.CV arXiv submitted 2026-08-03Network maps solar cell crack pixels to lost watts
Shanaka Ramesh Gunasekara +4 · “STC-Net: Electroluminescence-Based Solar Cell Crack Segmentation for Power Loss Estimation”
2608.01714 -
cs.AI arXiv submitted 2026-08-03Explicit knowledge layer matches published meta-analyses 57/58
Lingbo Li +2 · “Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis Using an Agentic Harness”
2608.01711 -
cs.AI arXiv submitted 2026-08-03Durable state, not single-use tokens, stops agent replays
Jinghan Xu +4 · “Beyond Single-Use Tokens: Durable Authorization State for Replay-Resistant LLM Agent Actions”
2608.01710 -
cs.CV arXiv submitted 2026-08-03One photo, no fine-tuning: nearest-object distances to 0.26 m
Hai Nguyen +2 · “SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models”
2608.01709 -
cs.CL arXiv submitted 2026-08-03Tying personas to their evidence sharpens small-model agents
Wonjun Choi +3 · “PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents”
2608.01708 -
cs.NI arXiv submitted 2026-08-03Clos beats torus for most ML training traffic
Sarah McClure +6 · “On Topology's Role in ML Training Performance”
2608.01707 -
cs.CV arXiv submitted 2026-08-03Sim(3) graph cuts feed-forward SLAM drift by up to 46%
Inha Lee +3 · “UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization”
2608.01706 -
cs.CY arXiv submitted 2026-08-03Six pillars frame what K-12 teachers need to know about GenAI
Shahin Hossain +9 · “Rethinking Generative AI Literacy: An Integrative, Developmental, and Dialectical Framework for K-12 Teacher Education”
2608.01705 -
cs.IR arXiv submitted 2026-08-03Five-model fusion reaches 60% of the possible crowd-highlight score
Kazuki Nakayashiki +1 · “Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?”
2608.01704 -
eess.SY arXiv submitted 2026-08-03Amplify-then-attenuate feedback pairs keep control signals bounded
Arthut Castello B. de Oliveira +2 · “On input-output persistency and the interconnection of positive nonlinear systems”
2608.01699 -
cs.RO arXiv submitted 2026-08-03Inertia fix in simulator cuts robot-leg sim-to-real errors by 80%
Jinsong Hong +4 · “Bridging the Sim-to-Real Gap in Parallel-Link Leg Mechanisms via Simulator-Side Dynamics Normalization”
2608.01697 -
cs.CV arXiv submitted 2026-08-03Keeping player roles separate lifts action-spotting F1 to 0.778
Ruifeng Wang +2 · “Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting”
2608.01696 -
cs.HC arXiv submitted 2026-08-03No-score VR neck rehab relaxes users
David Perron +6 · “Beyond Score-Based Gamification: Designing Spatiotemporal and Musical Experiences for VR Neck Rehabilitation”
2608.01688 -
cs.CV arXiv submitted 2026-08-03Scaling laws point to national medical AI without big tech
Masahiro Oda · “Generative AI and Foundation Models in Medical Image”
2608.01686 -
cs.AI arXiv submitted 2026-08-03Below 40%: LLM agents fail most complex graph tasks
Jiarui Tan +7 · “GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks”
2608.01684 -
cs.AI arXiv submitted 2026-08-03Memory consolidation erases authority in 48 of 49 setups
Qiuyang Zhan +4 · “When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary”
2608.01679 -
cs.LG arXiv submitted 2026-08-03RL-trained editor writes agent skills by testing each edit
Junhao Shen +3 · “Progressive Agent Skill Generation via Reinforcement Learning”
2608.01678 -
cs.CV arXiv submitted 2026-08-03Diffusion bridge turns routine cine MRI into DENSE-quality strain
Rishov Paul +2 · “Generative Brownian Bridge Diffusion In Motion Space For Enhanced Myocardial Strain Analysis”
2608.01677 -
cs.CL arXiv submitted 2026-08-03Block pruning rewires which evidence controls a model's answer
Xingyu Ren +3 · “Understanding Sparse Attention Selectivity in Long-Context Foundation Models via Counterfactual Evaluation”
2608.01676 -
cs.CL arXiv submitted 2026-08-03Distilling what to remember doubles long-context retrieval
Zixuan Wang +6 · “Learning What to Remember: Test-Time Training via Context Distillation”
2608.01672