pith. sign in

archive

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

14513 papers in cs.AI · page 19

  1. cs.LG 2026-05-18 reviewed
    RL trajectories match real customer paths better than TSP or PNN

    Modelling Customer Trajectories with Reinforcement Learning for Practical Retail Insights

    Ken Ming Lee +3

  2. cs.CV 2026-05-18 reviewed
    Accuracy unchanged when latent visual tokens replaced by dummies

    What's Holding Back Latent Visual Reasoning?

    Andr\'e G. Viveiros +3

  3. cs.AR 2026-05-18 reviewed
    Input flips extend multiplier life under NBTI aging

    Building Reliable Arithmetic Multipliers Under NBTI Aging and Process Variations

    Masoud Heidary +1

  4. cs.CR 2026-05-18 reviewed
    Clean experiences poison reflective LLM agents

    OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

    Kaixiang Wang +3

  5. cs.LG 2026-05-18 reviewed
    Dual self-distillation balances privacy and utility in LLMs

    It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

    Sangwoo Park +8

  6. cs.CL 2026-05-18 reviewed
    No memory method works consistently for LLM agents

    EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

    Yuyao Wang +9

  7. cs.CV 2026-05-18 reviewed
    Geometry-aware coresets lift VLM accuracy in pathology without training

    Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology

    Franciskus Xaverius Erick +2

  8. cs.CR 2026-05-18 reviewed
    Architectural proxy stops unauthorized LLM tool use

    Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control

    Rohith Uppala

  9. cond-mat.mes-hall 2026-05-18 reviewed
    AI robotic lab creates graphene and atomically thin transistors

    Qumus: Realization of An Embodied AI Quantum Material Experimentalist

    Lihan Shi +16

    5 Piths
  10. cs.CL 2026-05-18 reviewed
    Governed skill libraries boost frozen agents on benchmarks

    SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

    Hongyi Liu +5

  11. cs.CY 2026-05-18 reviewed
    Census simulations diagnose bias in Korean LLMs

    Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulation

    Sungwoo Kang

  12. cs.LG 2026-05-18 reviewed
    Graph model beats larger ones on long-range tasks with 1% parameters

    Graph Hierarchical Recurrence for Long-Range Generalization

    Stefano Carotti +5

  13. cs.RO 2026-05-18 reviewed
    Fixed camera network gives robots real-time shared indoor maps

    Towards Ubiquitous Mapping and Localization for Dynamic Indoor Environments

    Halim Djerroud +4

  14. hep-ph 2026-05-18 reviewed
    Hyper-GNN lifts four-top significance to 9.1 sigma

    Probing SMEFT Operators through $t\bar{t}t\bar{t}$ Production with Hyper-Graph Neural Networks at the LHC

    Amir Subba +1

  15. cs.AI 2026-05-18 reviewed
    LLMs beat chance on spatial reasoning but stumble on tough calculi

    QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi

    Anthony G. Cohn +1

    4 Piths
  16. cs.LG 2026-05-18 reviewed
    RL fine-tunes LLM to emit reusable solvers 91x cheaper than sampling

    Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers

    Soheyl Massoudi +3

  17. cs.HC 2026-05-18 reviewed
    AI mirrors user mistakes, lowering advice and performance

    The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration

    Cansu Koyuturk +2

  18. cs.HC 2026-05-18 reviewed
    AI mirrors user mistakes in collaborative ranking tasks

    The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration

    Cansu Koyuturk +2

  19. cs.CV 2026-05-18 reviewed
    Parameter-free attention matches CSRNet accuracy without extra parameters

    Optimising CSRNet with parameter-free attention mechanisms for crowd counting in public transport

    Aida Rostamza +3

  20. cs.CV 2026-05-18 reviewed
    KV selection per frame and head speeds video diffusion 1.48x

    Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion

    Peiliang Cai +10

  21. cs.SE 2026-05-18 reviewed
    Framework choice reverses meaning of agent behavior signals

    Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents

    Wei Ma +5

  22. cs.LG 2026-05-18 reviewed
    Feedback steers RL to faster learning and higher peaks

    FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning

    Xikai Zhang +8

  23. cs.AI 2026-05-18 reviewed
    Causal layer cuts SRE diagnosis time 63%

    Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows

    Dhairya Dalal +4

  24. cs.CV 2026-05-18 reviewed
    RAE v2 reaches SOTA gFID 1.06 in 80 epochs on ImageNet

    Improved Baselines with Representation Autoencoders

    Jaskirat Singh +5

  25. cs.LG 2026-05-18 reviewed
    Value interpolation expands offline RL action support

    ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy Optimization

    Yifei Chen +2

  26. cs.CV 2026-05-18 reviewed
    Wasserstein criterion boosts accuracy of small medical image QA models

    Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering

    Luca Hagen +4

  27. cs.LG 2026-05-18 reviewed
    Prior alignment speeds up re-alignment on re-exposure

    Alignment Dynamics in LLM Fine-Tuning

    Yuhan Huang +2

  28. cs.LG 2026-05-18 reviewed
    Port-Hamiltonian routing shrinks latent space by 4-8% in world models

    PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics

    Xueyu Luan +1

  29. cs.AI 2026-05-18 reviewed
    Self-distillation supplies step-level search signals from own rollouts

    SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning

    Yufei Ma +8

  30. cs.AI 2026-05-18 reviewed
    Aligning masked EEG views improves cross-dataset transfer

    DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

    Yang Shao +3

  31. cs.SE 2026-05-18 reviewed
    CommitDistill hits 0.75 retrieval rate from git history at 256-char budget

    CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories

    Divya Chukkapalli +4

  32. cs.CL 2026-05-18 reviewed
    Preference focus cuts device RAG memory 2400 times

    From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG

    Changmin Lee +2

  33. cs.LG 2026-05-18 reviewed
    Co-training cars and pedestrians cuts collisions 30 percent

    Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty

    Prakash Aryan +3

  34. cs.IR 2026-05-18 reviewed
    Prompting methods raise table QA accuracy without training

    Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting

    Amritansh Maurya +3

  35. cs.CV 2026-05-18 reviewed
    Shared codebook bridges modalities without full data pairs

    CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook

    Zeyu Chen +2

  36. cs.CL 2026-05-18 reviewed
    MDU unlearns data in masked diffusion models by KL reversal

    Machine Unlearning for Masked Diffusion Language Models

    Georu Lee +4

  37. cs.LG 2026-05-18 reviewed
    Privacy RL matches non-private sample bounds in continuous settings

    Privacy Preserving Reinforcement Learning with One-Sided Feedback

    Lin William Cong +3

  38. cs.CL 2026-05-18 reviewed
    Multi-turn chats in low-resource languages jailbreak LLMs

    Multilingual jailbreaking of LLMs using low-resource languages

    Dylan Marx +1

  39. cs.CL 2026-05-18 reviewed
    SomaliWeb v1 delivers 303M tokens of cleaned Somali text

    SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark

    Khalid Yusuf Dahir

  40. cs.LG 2026-05-18 reviewed
    Two SAE metrics fail basic reliability checks

    Are Sparse Autoencoder Benchmarks Reliable?

    David Chanin

  41. cs.CL 2026-05-18 reviewed
    Memory of precomputed states cuts LLM prefix attention costs

    Context Memorization for Efficient Long Context Generation

    Yasuyuki Okoshi +5

  42. cs.LG 2026-05-18 reviewed
    Simplex witness certifies input-dependent VAE encoder

    A Simplex Witness Certificate for Constant Collapse in Variational Autoencoders

    Zegu Zhang +2

  43. cs.CL 2026-05-18 reviewed
    GA-S2S adds k-hop graph structure to raise link prediction 19%

    Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction

    Luu Huu Phuc +5

  44. cs.CV 2026-05-18 reviewed
    Question routing lifts zero-shot spatial video QA by up to 5%

    SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot Spatial Reasoning

    Pawat Chunhachatrachai +3

  45. cs.LG 2026-05-18 reviewed
    COCOCO gives conformal sets that obey logic and stay small

    Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models

    Samuele Bortolotti +4

  46. cs.IR 2026-05-18 reviewed
    LLM pseudoqueries from table profiles improve dataset search

    PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries

    Riccardo Terrenzi +3

  47. cs.RO 2026-05-18 reviewed
    RGB cameras build 3D scene graphs for robots as well as depth sensors

    RGB-only Active 3D Scene Graph Generation for Indoor Mobile Robots

    Giorgia Modi +3

  48. cs.AI 2026-05-18 reviewed
    Sensory-bounded reasoning lifts MLLM accuracy on second-order belief tasks

    Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks

    Yajing Zhou +1

  49. cs.AI 2026-05-18 reviewed
    Pairwise preferences boost alignment and diversity in open generation

    Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation

    Guining Cao +5

  50. cs.RO 2026-05-18 reviewed
    External cameras boost robot scene recall by up to 79%

    Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation

    Giorgia Modi +3