Pith. sign in

INDEX

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

102,155 reviewed papers in cs · newest first · page 1

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 2026-08-05
    Full-context model wins multi-turn image retrieval

    Shengcao Cao +8 · “CoCo-IR: Contextual Composed Image Retrieval”

    2608.05149
  2. cs.CL arXiv submitted 2026-08-05
    50 procedural generators beat three rival reasoning datasets

    Damien Sileo +2 · “Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training”

    2608.05148
  3. cs.CV arXiv submitted 2026-08-05
    Few taps plus photos reconstruct an object's sound

    Zisen Shao +3 · “Objects as Audio-Visual Modal Sound Fields”

    2608.05145
  4. cs.AI arXiv submitted 2026-08-05
    Agent runtime hits 78% on SWE-Bench Pro without retraining

    Boxiu Li +25 · “Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning”

    2608.05144
  5. cs.AI arXiv submitted 2026-08-05
    12% cross-repo code in the training mix lifts long-context skills

    Indraneil Paul +3 · “OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling”

    2608.05141
  6. cs.CL arXiv submitted 2026-08-05
    Skill entropy predicts and fixes LLM skill-switching drops

    Yinghui He +8 · “Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning”

    2608.05139
  7. eess.AS arXiv submitted 2026-08-05
    Fine-tuned 1B retriever beats 8B embedders and BM25 on Greek

    Ayoub Kirouane +1 · “Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains”

    2608.05138
  8. cs.CV arXiv submitted 2026-08-05
    Adaptive modality mixing beats fixed fusion on five 3D benchmarks

    Yue Zhang +4 · “SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding”

    2608.05137
  9. cs.LG arXiv submitted 2026-08-05
    Gauge symmetry decides which optimizers keep the low-rank bias

    Devender Singh · “The Loss Does Not See the Basis, but Adam Does”

    2608.05136
  10. cs.HC arXiv submitted 2026-08-05
    Turn vague research goals into vetted collaborator shortlists

    Yingchaojie Feng +4 · “DeepConnect: A Visual Analytics System for Bridging Interdisciplinary Research Collaborations”

    2608.05134
  11. cs.CV arXiv submitted 2026-08-05
    Brain shape forecast beats the 'no-change' baseline by 2.29%

    Hao Ding +3 · “Predicting Brain Morphometry with MT-GNN: Mesh Evolution in Continuous Time with Graph-Based Metric Tensor Embeddings”

    2608.05132
  12. cs.CV arXiv submitted 2026-08-05
    Balance-aware distillation lifts a 4B MLLM to 80%

    Aniri +7 · “OPD-V: Visual On-Policy Self-Distillation with Modality Balance”

    2608.05131
  13. cs.CL arXiv submitted 2026-08-05
    Function calls beat intent-and-slot parsing for spoken AI

    Yuezhang Peng +5 · “Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models”

    2608.05126
  14. cs.CL arXiv submitted 2026-08-05
    Chained fresh LLM calls gain 13.75 points on long-context tasks

    Purbesh Mitra +1 · “Chained Recursive Language Models for Multi-Iteration Reasoning”

    2608.05124
  15. cs.CV arXiv submitted 2026-08-05
    Frozen ViT orientation peaks pick the best fine-tuning depth

    Vaishnavi B Mohan +3 · “IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers”

    2608.05122
  16. cs.SE arXiv submitted 2026-08-05
    AI coding tools' visual barriers fall into three recurring types

    Sabrina Haque +1 · “Characterizing Visual Accessibility Issues in AI Developer Tools: An Empirical Study”

    2608.05116
  17. cs.CV arXiv submitted 2026-08-05
    Pose-only student beats larger models on classroom incidents

    Paritosh Parmar +4 · “Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition”

    2608.05115
  18. stat.ML arXiv submitted 2026-08-05
    SCMS converges to a stable ridge

    Wanli Qiao · “Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift”

    2608.05112
  19. cs.LG arXiv submitted 2026-08-05
    Same bonus amplifies, equalizes, or nulls—reward structure decides

    Jai Malegaonkar +2 · “Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning”

    2608.05111
  20. quant-ph arXiv submitted 2026-08-05
    One shared random bit outpowers shallow unitary quantum models

    Arunava Majumder +3 · “Representational separation between unitary and channel quantum generative models via shared classical randomness at shallow depth”

    2608.05110
  21. eess.IV arXiv submitted 2026-08-05
    Single-shot laparoscopic depth hits 26 Hz without projector sync

    Wayne Wonseok Rodgers +7 · “AI-based single-shot structured-light depth reconstruction for real-time laparoscopic surgical guidance”

    2608.05109
  22. cs.CR arXiv submitted 2026-08-05
    Memory-augmented attacker closes prompt-injection red-teaming gap

    Yanting Wang +3 · “Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming”

    2608.05108
  23. cs.AI arXiv submitted 2026-08-05
    CoPlan lets care planners edit AI reasoning before the final plan

    Hung Truong Thanh Nguyen +6 · “CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs”

    2608.05107
  24. cs.LG arXiv submitted 2026-08-05
    Stripped to 10% of its weights

    Sajib Hossain +4 · “BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning”

    2608.05104
  25. cs.LG arXiv submitted 2026-08-05
    One frozen weather prior runs filtering

    Dibyajyoti Chakraborty +1 · “Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Flow-matching”

    2608.05103
  26. cs.AI arXiv submitted 2026-08-05
    4B agent hits 55% on BrowseComp via answer-backtracked step credit

    Yijun Lu +6 · “ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment”

    2608.05102
  27. cs.CV arXiv submitted 2026-08-05
    Mask-free detector beats CT deepfake baselines by 9 AUC

    Orazio Pontorno +3 · “HexMIL: Hierarchical Attention MIL for Ante-Hoc Explainable Detection of AI-Manipulated CT Volumes”

    2608.05101
  28. cs.CV arXiv submitted 2026-08-05
    A 4x sharper lesion signal in pretraining lifts frozen CT detection

    Mahmut S. Gokmen +5 · “Lesion Detection in CT with Frozen Self-Distilled Features: SALT, a Spatially Adaptive Label-Guided Temperature”

    2608.05100
  29. cs.CL arXiv submitted 2026-08-05
    Most LLMs ignore the modal logic they are told to use

    R\'eemi Andrieu +1 · “Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?”

    2608.05097
  30. cs.AI arXiv submitted 2026-08-05
    Localized memory paths lift LLM agents using 7% of tokens

    Xiawei Yue +4 · “Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite”

    2608.05095
  31. cs.LG arXiv submitted 2026-08-05
    Diagonally preconditioned Muon beats Muon at GPT-2 pretraining

    Tongle Wu +3 · “MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning”

    2608.05088
  32. cs.PF arXiv submitted 2026-08-05
    Falcon-512 fits C-V2X, fails 90% delivery above lightest traffic

    Akid Abrar +6 · “Deployment Feasibility Analysis of Post-Quantum Digital Signatures in Safety-Critical C-V2X Communication for Urban Mobility Scenario”

    2608.05087
  33. cs.AI arXiv submitted 2026-08-05
    AI safety benchmarks reduce to three hidden traits

    Joshua Fonseca Rivera (1) +4 · “Item Response Theory for AI Safety”

    2608.05086
  34. cs.LG arXiv submitted 2026-08-05
    Every fixed-lookahead experiment rule can be arbitrarily suboptimal

    Ahmed Hassoon +1 · “Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection”

    2608.05085
  35. cs.LG arXiv submitted 2026-08-05
    Diffusion policies run 2.7x faster by learning when to stop denoising

    Rohit Kumar Salla +2 · “Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control”

    2608.05084
  36. cs.LG arXiv submitted 2026-08-05
    A learned rollout controller beats uniform sampling and fixed rules

    Zheyuan Zhang +10 · “Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning”

    2608.05080
  37. cs.RO arXiv submitted 2026-08-05
    SpikingNav lifts corrupted ObjectNav success from 8.45% to 13.71%

    Jiahong Zhang +7 · “SpikingNav: Robust Embodied Navigation with Spiking Neural Policies”

    2608.05078
  38. cs.CV arXiv submitted 2026-08-04
    Shared-backbone branches beat single-branch multimodal models

    Yang Yang +7 · “ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs”

    2608.04010
  39. cs.CL arXiv submitted 2026-08-04
    Best LLM scores 75/100 forecasting anonymized social events

    Zhenran Wang +3 · “SocietyBench: Forecasting Counterfactual Social-World Evolution”

    2608.04009
  40. cs.CL arXiv submitted 2026-08-04
    Six LLMs matched the bookies on live World Cup picks

    Zhenran Wang +3 · “WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament”

    2608.04008
  41. cs.CL arXiv submitted 2026-08-04
    TurnSight beats prior best tool-use RL by 7.7%

    Changle Qu +6 · “TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning”

    2608.04007
  42. cs.HC arXiv submitted 2026-08-04
    Trustworthiness metrics lift expert agreement on LLMs

    Adam Coscia +4 · “Calibrating Trustworthiness: Co-Designing Metrics and Visualizations for Evaluating LLMs in Education”

    2608.04006
  43. cs.CL arXiv submitted 2026-08-04
    Personal agents do improve from memory—unevenly

    Shuhan Xue +8 · “PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents”

    2608.04003
  44. math.NA arXiv submitted 2026-08-04
    ROM misfit cuts clean layered-inversion error 14-fold

    Konstantinos Alexopoulos +1 · “Reduced-order modeling for electromagnetic inverse problems: a layered medium benchmark”

    2608.03996
  45. cs.CL arXiv submitted 2026-08-04
    ALiBi's distance bias silently blinds attention heads at long contexts

    Christopher Schr\"oder +4 · “When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings”

    2608.03994
  46. cs.CV arXiv submitted 2026-08-04
    Text calibration lifts training-free segmentation by up to 5.9 pts

    Wanli Ma +3 · “Perceptual Anchoring: Prototype-Guided Text Calibration for Training-free Open-Vocabulary Semantic Segmentation”

    2608.03991
  47. cs.LG arXiv submitted 2026-08-04
    Pathology-trained metrics predict which synthetic images help

    Seyed Kahaki +3 · “Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation”

    2608.03990
  48. cs.CL arXiv submitted 2026-08-04
    Browser workbench runs string algorithms 2,500x faster

    Mirac Suzgun +3 · “string2string Studio: An Interactive, In-Browser Platform for String-to-String Algorithms”

    2608.03984
  49. cs.PL arXiv submitted 2026-08-04
    Best LLM recovers compiler-missed speedups on 83% of attempts

    Hailong Jiang +6 · “Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss?”

    2608.03983
  50. cs.CV arXiv submitted 2026-08-04
    Video agent tops Claude-4.5, GPT-5 by grounding before searching

    Zhen Fang +19 · “Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent”

    2608.03979