Pith. sign in

INDEX

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

75,713 reviewed papers in cs · newest first · page 3

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.CV arXiv submitted 2026-07-14
    VLMs gain 28 points on cross-image comparison with triplet rewards

    Lin Peng +4 · “CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models”

    2607.12786
  2. cs.CV arXiv submitted 2026-07-14
    Diffusion-guided Gaussians clean up unseen endoscopic anatomy

    Cheng-Tai Hsieh +8 · “ExtraGS: Enhancing Endoscopic View Extrapolation via Diffusion-Guided 3D Gaussian Splatting”

    2607.12785
  3. cs.RO arXiv submitted 2026-07-14
    Safety layer only kicks in when robots head toward danger

    Paolo Magliano +4 · “Directional Constraints for Efficient Exploration in Safe Reinforcement Learning”

    2607.12784
  4. cs.CV arXiv submitted 2026-07-14
    Keep every spectral band, train only ~2% of the model

    Mingzhen Xu +11 · “MBTI: A Multi-Branch Efficient Fine-Tuning Framework for Hyperspectral Image Classification with Foundation Models”

    2607.12782
  5. quant-ph arXiv submitted 2026-07-14
    Transformers hit a length wall on exact quantum circuits

    Mehdi Saeedi +2 · “When Close Enough Is Not Enough: Autoregressive Drift in Quantum Circuit Synthesis”

    2607.12780
  6. math.OC arXiv submitted 2026-07-14
    Learning ADMM makes scenario MPC fast enough for real time

    Trinh Tran +2 · “Learning-enabled Acceleration of Scenario-based Model Predictive Control”

    2607.12775
  7. cs.CV arXiv submitted 2026-07-14
    Frozen light models beat heavy ABAW baselines with calibration

    Aleksei Bakin +1 · “HSEmotion Team at the 11th ABAW Challenge: Multi-Task Learning and Ambivalence/Hesitancy Video Recognition”

    2607.12774
  8. cs.LG arXiv submitted 2026-07-14
    30B LLM beats specialized model on exact reaction pathways

    Xingyu Dang +3 · “Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models”

    2607.12771
  9. cs.AI arXiv submitted 2026-07-14
    Bayesian score ends length bias in multiple-choice LM tests

    Koen Oostermeijer · “Accuracy and Normalized Accuracy under Length Bias: Analysis, Guidelines, and a Bayesian Alternative”

    2607.12767
  10. cs.CR arXiv submitted 2026-07-14
    Cloud-orchestrated QKD network spans three vendors and non-QKD domains

    Konstantinos Krilakis +3 · “A Scalable Cloud-Orchestrated and Service-Oriented Multi-Domain QKD Network with PQC Integration”

    2607.12765
  11. cs.CV arXiv submitted 2026-07-14
    Agent rewrites its own knowledge hypergraph mid-reasoning

    Jiashi Lin +14 · “EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval”

    2607.12764
  12. cs.LG arXiv submitted 2026-07-14
    Penalty weights make federated RL microgrids safer than FedAvg

    Usman Haider +1 · “Constraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination”

    2607.12763
  13. math.NA arXiv submitted 2026-07-14
    Mesh-free solver keeps every phase area exact in multi-phase flow

    Tokuhiro Eto · “A Structure-Preserving Method of Fundamental Solutions for the Multi-Phase Mullins-Sekerka Flow”

    2607.12759
  14. cs.CV arXiv submitted 2026-07-14
    One VLM compresses its own visual tokens into a few memory slots

    Yupeng Zheng +3 · “VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression”

    2607.12756
  15. cs.HC arXiv submitted 2026-07-14
    Judgment and virtue can blunt the risks of opaque AI

    Nathan G. Wood +1 · “Practical Judgment, Virtue, and Intuition in the Use of Opaque AI-Enabled Systems”

    2607.12755
  16. cs.CV arXiv submitted 2026-07-14
    Flow starts from the low-quality image

    Shuwei Huang +4 · “RFMSR: Residual Flow Matching for Image Super-Resolution”

    2607.12753
  17. cs.CV arXiv submitted 2026-07-14
    LMMs detect and fix 3D/4D hallucinations without retraining

    Hongbo Wang +5 · “Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation”

    2607.12752
  18. cs.CV arXiv submitted 2026-07-14
    Public dataset grades colorectal cancer at four magnifications

    Elham Amjadi +6 · “CRC-HGD: A Histopathological Image Dataset for Grading Colorectal Cancer”

    2607.12750
  19. cs.CV arXiv submitted 2026-07-14
    Satellite tiles shrink to 71 ranked dairy-farm candidates

    Usman Haider +2 · “Weakly Supervised Spatio-Temporal Candidate Discovery of Dairy Farm Sites from Seasonal Satellite Imagery”

    2607.12748
  20. cs.AI arXiv submitted 2026-07-14
    Train on 100 successes, then flag the steps that break agent runs

    Samuel Yeh +3 · “Tracing Agentic Failure from the Flow of Success”

    2607.12747
  21. cs.CV arXiv submitted 2026-07-14
    Coupled camera-display map doubles color fidelity

    Ruikang Li +5 · “Color Pass-Through via Camera-Display Coupling”

    2607.12746
  22. cs.CR arXiv submitted 2026-07-14
    Graph fragility sets how often encrypted fleets must re-key

    Sai Sandeep Damera +1 · “Stability Buys Time: A Re-Keying Game for Encrypted Multi-Agent Control”

    2607.12742
  23. cs.CL arXiv submitted 2026-07-14
    Stance flexibility under prompts is orthogonal to model capability

    Binwen Liu +1 · “Epistemic Stance Flexibility Probing: Measuring Prompt-Conditioned Register Shift in Large Language Models”

    2607.12739
  24. cs.HC arXiv submitted 2026-07-14
    AI research assistants should serve teams

    Diya Mirji +11 · “A\"ira: Rethinking AI Research Assistants for Interdisciplinary Science”

    2607.12736
  25. cs.LG arXiv submitted 2026-07-14
    Label-free prior speeds grokking 2.7× more reliably than labels

    Gunner Levi Howe · “What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking”

    2607.12735
  26. cs.AI arXiv submitted 2026-07-14
    LLMs spot mutated formal systems but miss the rule changes

    Julius Steiglechner +2 · “LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos”

    2607.12733
  27. cs.RO arXiv submitted 2026-07-14
    Every particle stays feasible

    Jiayun Li +1 · “Globalized Constrained Stein Variational Inference for Diverse Feasible Robot Motion Planning”

    2607.12732
  28. cs.LG arXiv submitted 2026-07-14
    Uncertainty placement is backbone-dependent once inputs are reconstructed

    Sarah Al-Shareeda +2 · “Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty”

    2607.12730
  29. hep-ph arXiv submitted 2026-07-14
    XGBoost maps non-Gaussian HEP likelihoods without losing physics

    Jorge Alda +3 · “Physically Consistent Parameter Inference: Transparent Machine Learning Emulation in High Energy Physics and Cosmology”

    2607.12726
  30. cs.SD arXiv submitted 2026-07-14
    Codec tokens morph source rhythm with palette timbre

    Emmanouil Karystinaios · “Neural Morphing: Sequence-Optimized Token-Level Morphing in Neural Audio Codecs”

    2607.12725
  31. cs.CR arXiv submitted 2026-07-14
    LLMs plus formal checks auto-find and patch container path escapes

    Qiyuan Fan +5 · “Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities”

    2607.12723
  32. cs.NI arXiv submitted 2026-07-14
    Hybrid FA-PSO recovers wall material parameters near the CRLB

    Zhuowei Li +9 · “High-Precision Hybrid FA-PSO Based Inversion of Building Material Parameters for Fundamental Wireless Performance Evaluation”

    2607.12721
  33. cs.DB arXiv submitted 2026-07-14
    Tables retrieved as joinable graphs

    Daomin Ji +4 · “GRAFT: Graph-Matched Retrieval and Fusion of Tables in Data Lakes”

    2607.12717
  34. cs.CR arXiv submitted 2026-07-14
    USB dongle encrypts whole disks

    Enrique Soriano-Salvador +1 · “Auditable and Transparent Fully Authenticated Disk Encryption via USB Storage Interposition”

    2607.12716
  35. math.NA arXiv submitted 2026-07-14
    Mass-conserving dynamics turn saddles into stable states

    Longjing Li +2 · “Mass-Conserving Saddle Dynamics via Generalized Inner Product: Theory, Algorithms, and Applications”

    2607.12715
  36. cs.IR arXiv submitted 2026-07-14
    Purchase as interest exit cuts post-buy redundancy by over 60%

    Yipin Dai +6 · “Learning to Forget: Satiation-Aware Long-Sequence Transducers for Mitigating Post-Purchase Redundancy”

    2607.12714
  37. cs.SE arXiv submitted 2026-07-14
    Line-anchored feedback cuts AI edit tokens up to 58%

    William Franz Lamberti · “Line-Anchored Feedback Cuts Token Costs and Improves Correctness in AI Code Editing”

    2607.12713
  38. cs.AI arXiv submitted 2026-07-14
    MaxSAT feedback lifts VLM Sudoku solves by keeping only consistent cells

    Pedro Orvalho +2 · “MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku”

    2607.12711
  39. cs.IT arXiv submitted 2026-07-14
    Superimposed symbols raise peak SE in hybrid massive MIMO

    Wei Jiang +1 · “Superimposed Transmission for Cooperative Cellular and Cell-Free Massive MIMO Systems”

    2607.12709
  40. cs.SD arXiv submitted 2026-07-14
    Edit one speech style category

    Haowei Lou +6 · “AutoSIFT: Automatic Style Sifting for Controllable Speech Generation with Arbitrary Style Infilling”

    2607.12706
  41. cs.CV arXiv submitted 2026-07-14
    Per-label style mixing lifts multi-label aerial DG by 5 mAP

    Alaa Almouradi +1 · “Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification”

    2607.12704
  42. cs.RO arXiv submitted 2026-07-14
    Humanoid learns soccer dribbling from depth images alone

    Flavio Maiorana +7 · “Vision-Based Dribbling for Humanoid Soccer via Privileged Representation Learning”

    2607.12702
  43. eess.SY arXiv submitted 2026-07-14
    Converter power and grid strength jointly set VSC stability

    Alessandra Casiraghi (1) +5 · “Stability Analysis of Grid-Following and Grid-Forming Converters Connected to Generators”

    2607.12697
  44. cs.CL arXiv submitted 2026-07-14
    Cost-aware drafts cut MoE expert thrashing

    Jincheng Xie +6 · “Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts”

    2607.12696
  45. cs.IT arXiv submitted 2026-07-14
    THz pinching antennas beat phased arrays via proximity

    Wei Jiang +1 · “Pinching-Antenna-Assisted Terahertz Communications: Modeling and Benchmarking”

    2607.12695
  46. quant-ph arXiv submitted 2026-07-14
    Eleven quantum heat solvers ranked under one fixed contract

    Mahmoud Elkarargy +3 · “Quantum PDE Solvers in Practice: Application-Driven Benchmarking of the Heat Equation”

    2607.12688
  47. cs.CL arXiv submitted 2026-07-14
    PPO critic becomes the confidence signal for language number prediction

    Mehak Dhaliwal +4 · “From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation”

    2607.12687
  48. cs.CL arXiv submitted 2026-07-14
    Segregate then fuse: SeRIn hits SOTA multimodal sentiment scores

    Alexios Filippakopoulos +4 · “Segregate, Refine, Integrate: Decomposing Multimodal Fusion for Sentiment Analysis”

    2607.12686
  49. cs.CV arXiv submitted 2026-07-14
    Brain-only intensity fix lifts nnU-Net TBI lesion Dice to 0.63

    Inhwa Son +3 · “Lesion Segmentation in Moderate to Severe Traumatic Brain Injury: An nnU-Net Based Approach with Adaptive Normalization in the AIMS-TBI 2025 Challenge”

    2607.12684
  50. cs.CV arXiv submitted 2026-07-14
    Mamba swap cuts YOLO26 FLOPs 12% with near-zero accuracy loss

    Sheng-Wei Chan +6 · “MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26”

    2607.12681