pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

74322 papers indexed · page 42

  1. cs.LG 2026-05-20 reviewed
    Hidden states at paragraph boundaries tune verifier strictness

    The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering

    Yefan Zhou +5

  2. cs.LG 2026-05-20 reviewed
    Testbed embeds detectable hacks for automatic reward-gaming checks

    Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

    Amit Roth +4

  3. cs.CV 2026-05-20 reviewed
    Constraint engine turns AI drawings into verifiable geometry reasoning

    Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction

    Juncheng Hu +3

  4. cs.AI 2026-05-20 reviewed
    Text modeling of EV battery signals enables LLM fault diagnosis

    VBFDD-Agent for Electric Vehicle Battery Fault Detection and Diagnosis: Descriptive Text Modeling of Battery Digital Signals

    Joey Chan +2

  5. physics.optics 2026-05-20 reviewed
    Mid-IR imaging system delivers 25 mm field with edge enhancement

    Wide-field mid-infrared edge-enhanced upconversion imaging

    Mengyao Yu +7

  6. cs.LG 2026-05-20 reviewed
    RL scores full distributions to fix LLM regression

    Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression

    Jungsoo Park +6

  7. math.ST 2026-05-20 reviewed
    Maximizing naive bounds recovers misspecified Cramér-Rao bound

    Revisiting the Misspecified Cram\'er-Rao Bound

    Malaak Khatib +3

  8. cs.CV 2026-05-20 reviewed
    Scale-decoupled alignment improves remote sensing incremental detection

    STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection

    Yaoteng Zhang +3

  9. cs.CV 2026-05-20 reviewed
    Language priors fix long-tail bias in 3D point cloud clustering

    Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors

    Siqi Wei +6

  10. math.AP 2026-05-20 reviewed
    Addition theorems yield exact elastic potential matrices

    Addition Theorems for Real Vector Spherical Harmonics and Explicit Matrix Representations of the Quasi-Periodic Elastic Single Layer Potential

    Xin Feng

  11. cs.CV 2026-05-20 reviewed
    Open-source iris algorithms pass first official IREX evaluation

    Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition

    Siamul Karim Khan +2

  12. cs.CR 2026-05-20 reviewed
    Monitor reduces LLM agent covert channels to zero capacity

    An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress

    Alfredo Metere

  13. cs.CV 2026-05-20 reviewed
    Method generates editable 3D surfaces from hand sketches

    Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches

    Wenda Wang +6

  14. cs.CV 2026-05-20 reviewed
    Attention reweighting suppresses spurious features before CNN pooling

    Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations

    Kin Whye Chew +1

  15. cs.CV 2026-05-20 reviewed
    Designer ratings dataset lifts AI graphic scorer to 0.611 agreement

    TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design

    Haonan Zhu +4

  16. cs.CL 2026-05-20 reviewed
    Aligning task vectors to in-context next-token distributions lifts accuracy 9.2%

    Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning

    Jihoon Kwon +2

  17. cs.CL 2026-05-20 reviewed
    Framework synthesizes realistic conversational retrieval benchmarks

    MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks

    Junhao Ruan +10

  18. cs.CV 2026-05-20 reviewed
    Early high-frequency injection reduces OOD score overlap

    Early High-Frequency Injection for Geometry-Sensitive OOD Detection

    Chuanjie Cheng +5

  19. cs.CV 2026-05-20 reviewed
    Virtual outliers reshape geometry to handle noisy labels

    GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels

    Ningkang Peng +6

  20. stat.ME 2026-05-20 reviewed
    Conformal tests bound false discoveries for every possible threshold

    Everywhere Valid Bounds on False Discovery Proportions in Conformal Inference

    Ziang Song +2

  21. cs.CV 2026-05-20 reviewed
    Decoupling reliabilities lifts noisy-label accuracy

    Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label

    Jingyang Mao +2

  22. cs.IR 2026-05-20 reviewed
    Dual memory layers give LLMs unbounded conversation context

    CALMem : Application-Layer Dual Memory for Conversational AI

    Rajendra Narayan Jena +2

  23. cs.LG 2026-05-20 reviewed
    Android crowds run large DNNs at 43 MB RAM per phone

    Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds

    Lakshani Manamperi +4

  24. cs.LG 2026-05-20 reviewed
    Group statistics adapt clipping and temperature to lift LLM math scores

    AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback

    Miaobo Hu +7

  25. math.RT 2026-05-20 reviewed
    Functor l preserves tilting pairs in cleft extensions

    Tilting pairs and Wakamatsu tilting pairs of subcategories over cleft extensions

    Guoqiang Zhao +1

  26. cs.LG 2026-05-20 reviewed
    GMM calibration lets recommenders use all noisy feedback

    Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework

    Zongyu Li +5

  27. math.NT 2026-05-20 reviewed
    Non-elliptic terms give o(X) errors in summed GL2 trace formula

    Beyond endoscopy for $\mathsf{GL}_2$ over $\mathbb{Q}$ with ramification 4: contribution of non-elliptic parts

    Yuhao Cheng

  28. math.OC 2026-05-20 reviewed
    Explicit Gâteaux formula yields mean-field policy gradient

    Policy Gradient for Continuous-Time Mean-Field Control

    Erhan Bayraktar +3

  29. cs.NE 2026-05-20 reviewed
    ReRAM macro reaches 419 TOPS/W for edge neural inference

    E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference

    Ankit Kumar Tenwar +2

  30. cs.LG 2026-05-20 reviewed
    Decision path flips raise random forest accuracy

    Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification

    Youngjoon Park

  31. cs.LG 2026-05-20 reviewed
    Decision-path flips yield unbiased per-sample weights for random forests

    Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification

    Youngjoon Park

  32. math.AP 2026-05-20 reviewed
    Scattering-blowup split holds at energy threshold for 4d NLS

    Threshold dynamics for the 4$d$ mass-energy double critical NLS

    Alex H. Ardila +3

  33. astro-ph.IM 2026-05-20 reviewed
    Multiple formats complicate astronomy visualization tools

    Data Formats and Visualisation BoF

    Keith Shortridge

  34. cs.CV 2026-05-20 reviewed
    SAVER selectively activates vision to boost F1 and cut latency in multimodal IE

    SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction

    Miaobo Hu +7

  35. cs.CL 2026-05-20 reviewed
    Categorical error rates beat WER for Indic speech recognition

    SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR

    Kavya Manohar +3

  36. math.OC 2026-05-20 reviewed
    New algorithm respects constraint priorities even when infeasible

    Augmented Lagrangian methods for convex optimization with priority constraints via an infeasibility control framework

    Yuya Yamakawa +2

  37. stat.ME 2026-05-20 reviewed
    New method checks observational CATE predictions against trial results

    Assessing Estimate of CATE from Observational Data via an RCT Study

    Bosen Cui +1

  38. cond-mat.soft 2026-05-20 reviewed
    35% of non-periodic packings show selective order

    What Lies Between Crystal and Randomly Packed Structures? A General Characterization of Non-Periodic Order

    Ian Douglass +1

  39. cs.CV 2026-05-20 reviewed
    DAR cuts DiT training iterations by 8.75x while improving FID by 2.11

    Rethinking Cross-Layer Information Routing in Diffusion Transformers

    Chao Xu +11

  40. math.NT 2026-05-20 reviewed
    GL(3) Fourier sums scaled by x^{-1/3} have a limiting distribution

    Limiting Distribution and Rate of Convergence for GL(3) Fourier Coefficients

    Zongqi Yu

  41. cs.DC 2026-05-20 reviewed
    WebGPU backend cuts LLM memory use by 29-33% in browsers

    Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU

    Reese Levine +7

  42. math.CO 2026-05-20 reviewed
    Forbidden s-point pattern forces sub-maximal incidences

    Extremal structure in dense arrangements of $k$-intersecting curves

    Andrew Suk +1

  43. cs.CR 2026-05-20 reviewed
    Heartbeat protocol revokes AI swarm credentials within fixed window

    Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms

    Saurabh Deochake

  44. quant-ph 2026-05-20 reviewed
    io-HEOM captures non-Markovian waveguide QED from two sources

    Strongly-coupled non-Markovian waveguide QED with input-output HEOM

    Neill Lambert +4

  45. cs.SE 2026-05-20 reviewed
    LLMs endorse 32% of their own behavior-changing code rewrites

    Articulate but Wrong: Self-Review Failures in LLM-Based Code Modernization

    Gokul Chandra Purnachandra Reddy +2

  46. math.PR 2026-05-20 reviewed
    Randomized Chirikov map mixes exponentially almost surely

    Quantitative exponential mixing for the randomized Chirikov standard map

    Ziyu Liu +1

  47. cs.HC 2026-05-20 reviewed
    AI simulator trains clinicians on disclosing medical errors

    CandorMD: An AI-Assisted Audio Simulation and Feedback System for Training Clinicians for Medical Error Disclosure

    Inna Wanyin Lin +6

  48. math.PR 2026-05-20 reviewed
    Gaussian limit holds for maxima under weaker correlation decay

    The maximum of a strongly correlated Gaussian process

    Jason Li +1

  49. cond-mat.str-el 2026-05-20 reviewed
    Substrate dipoles set 2D nonlinear conductivity to 1 μm/ΩV

    Giant nonlinear conductivity in 2D electron gas from substrate-induced dipolar scattering

    Dmitry V. Chichinadze +2

  50. astro-ph.GA 2026-05-20 reviewed
    Quasar ISM line ratios require heating beyond standard PDR models

    CO(7-6) and [C I](2-1) survey in z > 6 quasars

    Fuxiang Xu +15