pith. sign in

archive

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

14513 papers in cs.AI · page 16

  1. cs.LG 2026-05-19 reviewed
    Partial re-noising raises Sudoku accuracy from 56% to 75%

    Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement

    Taegu Kang +2

  2. cs.RO 2026-05-19 reviewed
    Evidence packets keep long-horizon robots aligned on task stages

    ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents

    Shuhan Guo +6

  3. cs.CV 2026-05-19 reviewed
    Gated CNN detects falls on smartwatches without attention

    You Don't Need Attention: Gated Convolutional Modeling for Watch-Based Fall Detection

    Sana Alamgeer +4

  4. cs.GR 2026-05-19 reviewed
    Diffusion model generates polycubes from point clouds for hex meshing

    PolycubeNet: A Dual-latent Diffusion Model for Polycube-Based Hexahedral Mesh Generation

    Lu He +7

  5. cs.RO 2026-05-19 reviewed
    Tuning converts robot delays into VLA performance gains

    DEFLECT: Delay-Robust Execution via Flow-matching Likelihood-Estimated Counterfactual Tuning for VLA Policies

    Yixiang Zhu +7

  6. cs.LG 2026-05-19 reviewed
    Decoupled recursion cuts interference in MLLM edits

    Modality-Decoupled Online Recursive Editing

    Siyuan Li +3

  7. cs.CL 2026-05-19 reviewed
    Metric selects only necessary rationales for LLM misinformation checks

    Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection

    Bing Wang +8

  8. cs.LG 2026-05-19 reviewed
    Trajectory selection beats sampling in delayed disambiguation

    EviTrack: Selection over Sampling for Delayed Disambiguation

    Omer Haq

  9. cs.CL 2026-05-19 reviewed
    End-to-end models output formal text straight from Chinese speech

    FormalASR: End-to-End Spoken Chinese to Formal Text

    Wanyi Ning +5

  10. cs.LG 2026-05-19 reviewed
    Small abstract spaces enable RL generalization to larger tasks

    Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning

    Nasehatul Mustakim +1

  11. cs.AI 2026-05-19 reviewed
    Stake-weighted votes approximate power to ownership in expectation

    Swimming with Whales: Analysis of Power Imbalances in Stake-Weighted Governance

    Yuzhe Zhang +3

  12. cs.SE 2026-05-19 reviewed
    Self-healing web apps detect faults at 90.7% and recover 56% faster

    When Web Apps Heal Themselves: A MAPE-K Based Approach to Fault Tolerance and Adaptive Recovery

    Sales Aribe Jr +1

  13. cs.AI 2026-05-19 reviewed
    Quadtrees cut GUI agent visual tokens by 30 percent

    AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees

    Yuankai Li +5

  14. cs.LG 2026-05-19 reviewed
    Python framework unifies XAI methods for ECG models

    ExECG: An Explainable AI Framework for ECG models

    Jong-Hwan Jang +1

  15. cs.AI 2026-05-19 reviewed
    Imbalanced attention heads bias MLLMs toward text errors over visuals

    Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination

    Jinrui Jiang +3

  16. cs.LG 2026-05-19 reviewed
    Local distance graphs recover global Euclidean embeddings

    Euclidean Embedding of Data Using Local Distances

    Dimitris Arabadjis

  17. cs.CV 2026-05-19 reviewed
    Post-training lifts video models' physical consistency

    PhyWorld: Physics-Faithful World Model for Video Generation

    Pu Zhao +12

  18. cs.CL 2026-05-19 reviewed
    Language access managers accept AI but require human oversight

    AI Technologies in Language Access: Attitudes Towards AI and the Human Value of Language Access Managers

    Miguel A. Jim\'enez-Crespo +2

  19. cs.AI 2026-05-19 reviewed
    Theory-anchored LLM cuts bias in disaster survey gaps

    Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responses

    Yan Wang +2

  20. cs.CL 2026-05-19 reviewed
    Step-level scores flag reasoning errors in closed LLMs

    Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

    Xiaoou Liu +5

  21. cs.CR 2026-05-19 reviewed
    Single trigger corrupts both text and image outputs in unified models

    Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

    Tobias Braun +4

  22. cs.CL 2026-05-19 reviewed
    LLM Uncertainty Scores Only Measure Output Consistency

    Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering

    Tiejin Chen +3

  23. cs.AI 2026-05-19 reviewed
    VLM agents match real A/B test shifts in 77 percent of cases

    SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents

    Han Li +19

  24. cs.CV 2026-05-19 reviewed
    PCA rotation aligns key channels for accurate VLM pruning

    Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference

    Beomseok Kang +4

  25. cs.AI 2026-05-19 reviewed
    Volatility increases exploration while stochasticity decreases it

    Not all uncertainty is alike: volatility, stochasticity, and exploration

    Payam Piray

  26. cs.CV 2026-05-19 reviewed
    Quantized model cuts brain tumor AI size by 6x with same accuracy

    Quantized Machine Learning Models for Medical Imaging in Low-Resource Healthcare Settings

    Sumanth Meenan Kanneti +1

  27. cs.RO 2026-05-19 reviewed
    RL quadrotor controller enables forest under-canopy inspections

    Aerial Inspection Behaviors via RL-based Quadrotor Control for Under-canopy Forest Environments

    Fausto Mauricio Lagos Suarez +4

  28. cs.LG 2026-05-19 reviewed
    PneumoNet hits 86.6% accuracy with 1.4% forgetting across device shifts

    On-Device Continual Learning with Dual-Stage Buffer and Dynamic Loss for Point-of-Care Pneumonia Diagnosis

    Danu Kim

  29. cs.AI 2026-05-18 reviewed
    Evidence certificates stop agents from unsafe hallucinated actions

    Hallucination as Exploit: Evidence-Carrying Multimodal Agents

    Guijia Zhang +2

  30. cs.AI 2026-05-18 reviewed
    Certified predicates stop hallucination exploits in agents

    Hallucination as Exploit: Evidence-Carrying Multimodal Agents

    Guijia Zhang +2

  31. cs.CY 2026-05-18 reviewed
    Global South red teaming uncovers unique T2I harms

    Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South

    Charvi Rastogi +15

  32. cs.AI 2026-05-18 reviewed
    Agents gain a profile to match KGs by what they can prove

    Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)

    Terry R. Payne +2

    1 Piths
  33. cs.LG 2026-05-18 reviewed
    Action-gap certificate certifies greedy goal reach in sparse planning

    Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning

    Shiheng Zhang

  34. cs.LG 2026-05-18 reviewed
    Retrieval memory sharpens forecasts for new delivery zones

    Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand

    Yihong Tang +5

  35. cs.AI 2026-05-18 reviewed
    AI agents produce 117 papers but none clear top-tier bar

    How Far Are We From True Auto-Research?

    Zhengxin Zhang +3

  36. cs.LG 2026-05-18 reviewed
    Wrapper gives pathwise risk control for updating LLMs

    Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs

    Hamed Khosravi +1

    4 Piths
  37. cs.AI 2026-05-18 reviewed
    Trust calibration for AI agents as preference learning

    Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool Use

    Changkun Ou

  38. cs.LG 2026-05-18 reviewed
    Sparse matrix bank gives SSMs dense-model expressivity

    Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models

    Aleksandar Terzi\'c +6

  39. cs.LG 2026-05-18 reviewed
    Low-rank bandits recover drifting subspaces from scalar rewards

    Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity

    Hamed Khosravi +1

    4 Piths
  40. cs.CR 2026-05-18 reviewed
    Benign rewriting lifts LLM safety against poisoning by 51 percent

    Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

    John T. Halloran +1

  41. cs.LG 2026-05-18 reviewed
    Local attack and support calls stabilize global argument rankings

    GRASP: Deterministic argument ranking in interaction graphs

    Diganta Misra +3

  42. cs.AI 2026-05-18 reviewed
    Neural Q-learning converges with finite-sample bounds in decentralized handoffs

    Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints

    Jiayu Li +4

    4 Piths
  43. cs.LG 2026-05-18 reviewed
    One model trained on text and time series matches both specialists

    Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding

    Paul Quinlan +3

  44. cs.RO 2026-05-18 reviewed
    Smartphones collect 7500 robot demos in five days

    COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones

    Ayush Agarwal +8

  45. cs.RO 2026-05-18 reviewed
    Smartphone teleop rivals specialized hardware for robot demos

    COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones

    Ayush Agarwal +8

  46. cs.CV 2026-05-18 reviewed
    SSL pretraining helps models know when to skip DR predictions

    Knowing When Not to Predict: Self Supervised Learning and Abstention for Safer DR Screening

    Muskaan Chopra +3

  47. cs.LG 2026-05-18 reviewed
    VLMs need tight data alignment and miss weak signals in egocentric video

    EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data

    Dongyan Lin +21

  48. cs.AI 2026-05-18 reviewed
    Frontier LLMs withhold 99% of protected data in agent tasks

    POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents

    Qiaoyuan Zheng +3

  49. cs.NE 2026-05-18 reviewed
    Graph diffusion solver reaches 100% feasibility on multi-objective scheduling

    GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization

    Xingyu Li

  50. cs.CV 2026-05-18 reviewed
    Diffusion model turns uniform organ maps into realistic PET scans

    Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model

    Suya Li +4