Pith. sign in

INDEX

Every paper Pith has read and judged, in one searchable index.

88,919 reviewed papers in cs · newest first · page 8

Pith rank means recent reader upvotes with each upvote's ranking weight halved after 24 hours. The archive itself is sorted by arXiv submission date.

  1. cs.AI arXiv submitted 2026-07-31
    Policy-space mixing beats reward mixing for multi-goal LLMs

    Ruiming Liang +8 · “Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL”

    2607.29246
  2. stat.ML arXiv submitted 2026-07-31
    Expected improvement is minimax-optimal

    Emmanuel Vazquez +1 · “Simple-regret rates and minimax optimality of fixed-prior expected improvement in Mat\'ern and squared-exponential RKHSs”

    2607.29245
  3. cs.CR arXiv submitted 2026-07-31
    JUNO's vector votes drop ACS messages to O(n^2)

    Liangrong Zhao +3 · “JUNO: Aggregated Vector Consensus for Optimal Asynchronous Common Subset”

    2607.29244
  4. cs.CV arXiv submitted 2026-07-31
    AI tool sizes aortic valves in minutes

    Alessandra Zerillo +6 · “TAVI-TEC: An AI-Based Tool for Procedural Planning of Transcatheter Aortic Valve Implantation”

    2607.29243
  5. cs.IR arXiv submitted 2026-07-31
    Bandit routing steadies LLM-driven recommender tuning

    Haoran Ling +7 · “RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems”

    2607.29241
  6. cs.CV arXiv submitted 2026-07-31
    Subtracting no-image bias lifts counterfactual accuracy 7.8 points

    Kesheng Chen +2 · “When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration”

    2607.29240
  7. cs.CL arXiv submitted 2026-07-31
    Tiny LoRA models match 7B on user-style rewriting

    Antorweep Chakravorty · “Small Is Enough: Per-User Style Rewriting of AI-Edited Text via LoRA Adapters”

    2607.29238
  8. cs.CV arXiv submitted 2026-07-31
    Zero-parameter scene flow ranks second and holds long range

    Minh-Quan Dao +3 · “CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation”

    2607.29237
  9. math.CO arXiv submitted 2026-07-31
    One search counts every triangle-maximal pseudoline arrangement to n=27

    Roman Parpalak +1 · “Enumeration and Classification of Triangle-Maximal Pseudoline Arrangements”

    2607.29236
  10. cs.RO arXiv submitted 2026-07-31
    Training-free feedback lifts robot success by 3 points

    Peize Li +5 · “FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution”

    2607.29235
  11. cs.RO arXiv submitted 2026-07-31
    Wearable $50 fingertip sensor lifts robot grasp success 40 points

    Yongxi Liu +6 · “TacPrint: A Wearable Fingertip Tactile Sensor for Human-to-Robot Contact Reproduction”

    2607.29231
  12. cs.NE arXiv submitted 2026-07-31
    SOMA candidate steps are exact linear maps

    Vojt\v{e}ch Nov\'ak +1 · “Linear Proposal Operators and Stochastic Search Geometry in SOMA and Differential Evolution”

    2607.29228
  13. cs.RO arXiv submitted 2026-07-31
    Event cameras beat RGB for teleop under bad light

    Haoyu Fu +6 · “Event-Based Upper-Body Humanoid Teleoperation Under Challenging Illumination”

    2607.29227
  14. cs.LG arXiv submitted 2026-07-31
    Gaussian-process BO loses the cost-quality trade-off across 17 tasks

    Panagiotis Krokidas +5 · “Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery”

    2607.29225
  15. cs.CV arXiv submitted 2026-07-31
    Beats supervised saliency models with no training on 13 benchmarks

    Wenzhuo Zhao +8 · “Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?”

    2607.29222
  16. cs.CR arXiv submitted 2026-07-31
    Masked matrix products make confidential 70B-model AI practical

    James Hsin-yu Chiang +3 · “MOSAIC: Masked Outsourcing of Secure AI Computations”

    2607.29221
  17. cs.AI arXiv submitted 2026-07-31
    Hidden Minecraft rules can help agents

    Jianxin Gao +8 · “MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft”

    2607.29218
  18. math.NA arXiv submitted 2026-07-31
    One number controls all 48 seventh-order error terms

    Zhixin Huo · “Certified Seventh-Order Two-Derivative Hermite Deferred Correction via Node-Sweep Co-Design”

    2607.29217
  19. cs.IR arXiv submitted 2026-07-31
    Multimodal RL alignment lifts delivery orders by 0.55%

    Jiping Liu +9 · “GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System”

    2607.29213
  20. cs.CL arXiv submitted 2026-07-31
    LLMs can learn when to quit: futile reasoning down to 1%

    Xinyan Guan +7 · “Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning”

    2607.29211
  21. cs.LG arXiv submitted 2026-07-31
    Anneal the teacher signal: stable fusion beats fixed mixing everywhere

    Yifan Ding +9 · “SAF-OPD: Stable Advantage Fusion for On-Policy Distillation”

    2607.29209
  22. cs.CV arXiv submitted 2026-07-31
    Dual semantic guidance lifts multi-spectral ReID from 47 to 64.6 mAP

    Weixiang Zhou +6 · “Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation”

    2607.29207
  23. cs.RO arXiv submitted 2026-07-31
    Ellipse per drone keeps swarm safety real-time in dense forests

    Alice Rosetti +4 · “MROPE: A Multi-Robot Safe Cooperative Strategy via combined Predictive Safety Filters and Ellipse-based Constraint Compression”

    2607.29203
  24. cs.CV arXiv submitted 2026-07-31
    Easy-first two-stage training sets new source-free adaptation records

    Pan Liu +5 · “Domain-Division based Progressive Learning for Source-Free Domain Adaptation”

    2607.29202
  25. cs.CV arXiv submitted 2026-07-31
    One model segments 13 ultrasound organs from text prompts alone

    Bo Xu +7 · “UltraSAM3: A Concept-Driven Foundation Model for Universal Ultrasound Image Segmentation”

    2607.29200
  26. cs.CR arXiv submitted 2026-07-31
    Multi-turn dialogue gives back ~20 points of guardrail safety

    Haoxin An +8 · “Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion”

    2607.29199
  27. cs.DC arXiv submitted 2026-07-31
    Checker catches every smart-home safety violation before execution

    Rishabh Menezes +4 · “Knox: Fortifying Smart Spaces With Safety Guarantees”

    2607.29198
  28. cs.CL arXiv submitted 2026-07-31
    Best of 22 chatbots passes just 41% of strict long-dialogue checks

    Eileen Ye +9 · “Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding”

    2607.29196
  29. eess.SY arXiv submitted 2026-07-31
    Software fix cuts short-circuit power rise by up to 36%

    Lukas Zezula +3 · “Interturn Short Circuit Fault Mitigation in PMSMs”

    2607.29195
  30. cs.CV arXiv submitted 2026-07-31
    Local-consistency term lifts few-shot RS scene classification

    Karim El Khoury +3 · “Locally Consistent Transductive Information Maximization for Few-Shot Remote Sensing Scene Classification”

    2607.29192
  31. cs.SC arXiv submitted 2026-07-31
    Exact proof settles 4x4 Dittert conjecture: uniform matrix wins

    Jinhui Li +2 · “A Proof of the Dittert Conjecture in Dimension 4 via an Agent-Guided Exact Sum-of-Squares Certificate”

    2607.29191
  32. cs.AI arXiv submitted 2026-07-31
    Certify the joint tool-return neighborhood

    Blaise Delattre +2 · “CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents”

    2607.29190
  33. cs.CL arXiv submitted 2026-07-31
    Automatic echo detection in migration stories peaks at r=0.38

    Sakayo Toadoum Sari +7 · “Detecting Experiential Intertextuality Across Migration Routes: Beyond Surface Similarity in French Narratives”

    2607.29188
  34. cs.DM arXiv submitted 2026-07-31
    Two antistrong packing problems are NP-complete

    Jiangdong Ai +3 · “The Complexity of Mixed Arc-Disjoint Spanning Subdigraphs with Antistrong Connectivity”

    2608.00115
  35. cs.CL arXiv submitted 2026-07-31
    Hidden reasoning traces sharpen AI preference judges

    Sanwoo Lee +5 · “Learning Latent Reasoning Traces for Scalar Reward Models End-to-End”

    2607.29185
  36. eess.IV arXiv submitted 2026-07-31
    Deep learning predicts skull ultrasound aberrations 2,535× faster

    Minju Seol +3 · “Few-shot Deep Learning for Phase-Amplitude Aberration Correction in Transcranial Focused Ultrasound”

    2607.29182
  37. cs.LG arXiv submitted 2026-07-31
    After eight passes, state machines beat frequency baselines

    Andy J. Phu +4 · “SERUM: State Extraction and Refinement for User Modeling”

    2607.29181
  38. cs.CV arXiv submitted 2026-07-31
    Flow-friendly latent tops text-to-motion without VQ or AR

    Yifei Zhu +5 · “MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation”

    2607.29180
  39. cs.SE arXiv submitted 2026-07-31
    Hackathon teams verify AI output even without explicit rules

    Wangyiyao Zhou +2 · “Quick Build, Careful Check? Generative AI Use in Hackathons”

    2607.29178
  40. cs.LG arXiv submitted 2026-07-31
    Behavior-aware diffusion fills utility data gaps up to 29% better

    Rongchao Xu +4 · “MBDiff: Multi-view Behavior-aware Diffusion Model for Probabilistic Utility Data Imputation”

    2607.29177
  41. eess.SP arXiv submitted 2026-07-31
    Predicting latent states lifts EEG transfer accuracy 10 points

    Jinhao Li +10 · “EEG-JEPA: Structured Latent Prediction for EEG Foundation Models”

    2608.00114
  42. cs.SE arXiv submitted 2026-07-31
    Execution-first training data beats query-first for tool agents

    Hafsa Ouajdi +5 · “Execution-First Synthetic Tool-Use Trace Generation for LLM Agents”

    2607.29175
  43. cs.DB arXiv submitted 2026-07-31
    MERIT makes graph-ANN vector deletion as cheap as insertion

    Zekai Wu +8 · “MERIT: Efficient In-Place Deletion for Dynamic Graph-Based Approximate Nearest Neighbor Indexes”

    2607.29173
  44. cs.DB arXiv submitted 2026-07-31
    Deleting vectors from ANN graphs now rivals insertion cost

    Zekai Wu +8 · “MERIT: Efficient In-Place Deletion for Dynamic Graph-Based Approximate Nearest Neighbor Indexes”

    2607.29173
  45. cs.RO arXiv submitted 2026-07-31
    Planner-guided drift AI laps faster than human drivers in simulation

    Sheng Zhao +3 · “Track-Guided Hierarchical Reinforcement Learning for Autonomous Vehicle Drifting with Minimum-Lap-Time Planning”

    2608.00113
  46. cs.RO arXiv submitted 2026-07-31
    Robot hits near-perfect success with no model access

    Yuxin Chen +9 · “CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning”

    2607.29172
  47. cs.RO arXiv submitted 2026-07-31
    Run-time guard lifts robot success from 49% to 90%

    Wenda Yu +5 · “ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency”

    2607.29169
  48. cs.CL arXiv submitted 2026-07-31
    N-grams beat transformers at verifying German video speakers

    Oren Halvani +1 · “Authorship Verification of Transcribed German-Language Videos”

    2607.29168
  49. cs.CR arXiv submitted 2026-07-31
    Blocks memory-laundered LLM agent attacks

    Jinghan Xu +4 · “Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory”

    2607.29167
  50. cs.CG arXiv submitted 2026-07-31
    Coverage beats 1-1/e for disks

    Sujoy Bhore +2 · “Approximation Algorithms for Geometric Maximum Coverage”

    2607.29160