pith. sign in

archive

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

14513 papers in cs.AI · page 21

  1. cs.CR 2026-05-18 reviewed
    Sparse attention heads let optimized obfuscation jailbreak LLMs

    Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling

    Ziwei Wang +8

  2. cs.AI 2026-05-18 reviewed
    SFT removes noisy token interactions in LLMs then overfits

    Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective

    Junpeng Zhang +5

  3. cs.SE 2026-05-18 reviewed
    Agentic RAG reaches 78% top-1 file bug localization

    BLAgent: Agentic RAG for File-Level Bug Localization

    Md Afif Al Mamun +1

  4. cs.CR 2026-05-18 reviewed
    Bézier paths connect adversarial examples for faster attacks

    MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks

    Hyo Seo Kim +5

  5. cs.CV 2026-05-18 reviewed
    Fewer semantic tokens match full multimodal performance

    A More Word-like Image Tokenization for MLLMs

    Hyun Lee +6

  6. cs.AI 2026-05-18 reviewed
    Agents reach 79% on game video frames

    SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain

    Lingtao Mao +6

    4 Piths
  7. cs.AI 2026-05-18 reviewed
    Benchmark shows agents at 79% on game video questions vs 95% oracle

    SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain

    Lingtao Mao +6

    4 Piths
  8. cs.CR 2026-05-18 reviewed
    Latent access to guard models speeds prompt-injection checks over 3x

    ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense

    Yash Narendra

  9. cs.LG 2026-05-18 reviewed
    Mirrored unlearning boosts data attribution in diffusion models

    Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

    Joan Serr\`a +4

  10. cs.CL 2026-05-18 reviewed
    BacktestBench tests LLMs on 18k backtesting QA pairs from real markets

    BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting

    Zhensheng Wang +5

  11. cs.CL 2026-05-18 reviewed
    Prompt compression fails to transfer to diffusion LLMs

    Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

    Sterling Huang +6

  12. cs.LG 2026-05-18 reviewed
    Transient expert steers MoE updates to cut forgetting

    CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning

    Yang Liu +2

  13. cs.DC 2026-05-18 reviewed
    Balancer halves imbalance in video diffusion transformer training

    AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training

    Yucheng Guo +8

  14. cs.DB 2026-05-18 reviewed
    DHNs capture unary negation fragment and counting extensions

    Expressive Power of Deep Homomorphism Networks over Relational Databases

    Moritz Sch\"onherr +5

  15. cs.LG 2026-05-18 reviewed
    One anchor pair identifies domain transfer under Jacobian sparsity

    Domain Transfer Becomes Identifiable via a Single Alignment

    Sagar Shrestha +3

  16. cs.AI 2026-05-18 reviewed
    Compiler enforces AI rules in constant time with formal proofs

    Ethical Hyper-Velocity (EHV): A Hardware-Rooted Zero-Trust Runtime Enforcement Architecture for Agentic AI Systems

    Riddhi Mohan Sharma

  17. cs.CV 2026-05-18 reviewed
    One model translates any sensor features to any other without retraining

    One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception

    Yang Li +9

  18. cs.AI 2026-05-18 reviewed
    AI chunking builds maps predicting war in Thucydides model

    Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap

    Akash Kumar Panda +2

  19. cs.AI 2026-05-18 reviewed
    Literature evidence anchors stochastic degradation model choice

    LAST-RAG: Literature-Anchored Stochastic Trajectory Retrieval-Augmented Generation for Knowledge-Conditioned Degradation Model Selection

    Hanbyeol Park +1

  20. cs.AI 2026-05-18 reviewed
    LLM voice agent hits 83.9% success on 400k daily calls

    DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

    Le Zhang +5

  21. cs.LG 2026-05-18 reviewed
    Single forward pass matches AlphaFold3 protein accuracy

    DCFold: Efficient Protein Structure Generation with Single Forward Pass

    Zhe Zhang +5

  22. cs.AI 2026-05-18 reviewed
    Benchmark rates AI agents by child cognitive age

    Evaluating Cognitive Age Alignment in Interactive AI Agents

    Yifan Shen +6

  23. cs.LG 2026-05-18 reviewed
    Inter-layer null signals cut attention sinks and boost quantized accuracy

    Attention Sinks and Outliers in Attention Residuals

    Haozheng Luo +12

  24. cs.CL 2026-05-18 reviewed
    AI agent teams beat human teams at generating creative ideas

    Multi-agent AI systems outperform human teams in creativity

    Tiancheng Hu +7

  25. cs.MM 2026-05-18 reviewed
    Two-phase sampling matches contradictory audio prompts to video

    CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation

    Gyubin Lee +2

  26. cs.DC 2026-05-18 reviewed
    Guard boosts training utilization 1.7x by catching hidden stragglers

    Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training

    Guanliang Liu +16

  27. cs.AI 2026-05-18 reviewed
    Internal probe plus attention head yields step rewards for agents

    PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

    Wonjoong Kim +4

  28. cs.LG 2026-05-18 reviewed
    Hindsight targets fix actions to cut agent training time 2.26x

    HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

    Woongyeng Yeo +3

  29. cs.LG 2026-05-18 reviewed
    Freshness control lets async distillation match sync results

    $\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control

    Xianwei Chen +2

  30. cs.CL 2026-05-18 reviewed
    New multi-accent dataset lowers ASR errors on technical talks

    PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions

    Sicheng Jin +2

  31. cs.AI 2026-05-18 reviewed
    This paper introduces Knowledge Infrastructure (KI)

    KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science

    Ziwei Li +7

  32. cs.LG 2026-05-18 reviewed
    State-action split lets GRPO train open-world VLM agents

    GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

    Xiongbin Wu +9

  33. cs.LG 2026-05-18 reviewed
    State-action decomposition adapts GRPO for VLM agents

    GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

    Xiongbin Wu +9

  34. cs.CL 2026-05-18 reviewed
    SynPro yields 3.7-5.2x more effective tokens from organic data

    Generating Pretraining Tokens from Organic Data for Data-Bound Scaling

    Zichun Yu +1

  35. cs.LO 2026-05-18 reviewed
    Retrieval system compresses Lean proofs over 70 percent

    Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search

    Jialin Lu +6

  36. cs.LG 2026-05-18 reviewed
    Bilevel optimization adapts distillation loss weights per sample

    Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization

    Anh B.H. Nguyen +2

  37. cs.CV 2026-05-18 reviewed
    Temporal pruning speeds video diffusion while preserving fidelity

    Temporal Aware Pruning for Efficient Diffusion-based Video Generation

    Sheng Li +5

  38. cs.CV 2026-05-18 reviewed
    Temporal smoothing lets pruning speed up video diffusion

    Temporal Aware Pruning for Efficient Diffusion-based Video Generation

    Sheng Li +5

  39. cs.LG 2026-05-18 reviewed
    One-step updates and barriers speed up noisy label correction

    Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning

    Ba Hoang Anh Nguyen +1

  40. cs.AI 2026-05-18 reviewed
    Memory-equipped agents show rising safety risks over time

    Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

    Ahmad Al-Tawaha +4

  41. cs.AI 2026-05-18 reviewed
    Interactive AI needs new rules for judging trajectories

    Interactive Evaluation Requires a Design Science

    Keyang Xuan +12

  42. cs.LG 2026-05-18 reviewed
    Orthogonal manifold moves identify content and style without independence

    Content-Style Identification via Differential Independence

    Subash Timilsina +3

  43. cs.CV 2026-05-18 reviewed
    VLMs count by prior instead of image when facts clash

    CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models

    Reem Alzahrani +5

  44. cs.CV 2026-05-18 reviewed
    Scene understanding training produces human-like fixations in foveated model

    Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding

    Shravan Murlidaran +3

  45. cs.DC 2026-05-18 reviewed
    TierCheck cuts LLM checkpointing time below 10 seconds

    TierCheck: Tiered Checkpointing for Fault Tolerance in Large Language Model Training

    Shujie Han +7

  46. cs.RO 2026-05-18 reviewed
    Topple actions speed up stack rearrangement plans

    Virtues of Ordered Chaos: Planning with Topple Actions in Tabletop Stack Rearrangement

    Hao Lu +1

  47. cs.AI 2026-05-18 reviewed
    Accountability boundary decides whether vertical AI firms lose value by going headless

    Going Headless? On the Boundaries of Vertical AI Firms

    Muhammad Zia Hydari +1

  48. cs.LG 2026-05-18 reviewed
    Shared Transformer Splits into Proposal and Uncertainty Roles

    One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer

    Jucheng Shen +2

  49. cs.AI 2026-05-18 reviewed
    PuppyChatter unifies SDK simplicity across AI vendors

    Accelerating AI-Powered Research: The PuppyChatter Framework for Usable and Flexible Tooling

    Chun-Hsiung Tseng +4

  50. cs.CV 2026-05-18 reviewed
    Reward variance selects learnable prompts for T2I training

    Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation

    Baoteng Li +10