The reviewed record of science sign in
Pith

archive

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

69392 papers in cs · page 1

  1. cs.CL 2026-07-08 reviewed
    Structural tokens let one model reason across proteins

    Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

    Chen Tang +28

  2. cs.CL 2026-07-08 reviewed
    Tiny model matches gpt-4o-mini on facts by offloading memory

    Co-LMLM: Continuous-Query Limited Memory Language Models

    Yair Feldman +7

  3. cs.LG 2026-07-08 reviewed
    Why delta-rule attention is the closest linear twin of softmax

    The Key to Going Linear: Analysis-Driven Transformer Linearization

    Anna Kuzina +2

  4. cs.DS 2026-07-08 reviewed
    Acyclic subgraphs beat spanning-tree bound in FPT time

    Exploiting Spanning Trees for Directed Acyclicity

    Sergei Khargeliia +1

  5. cs.CL 2026-07-08 reviewed
    Causal Slicing Finds Root Causes in Agent Traces

    From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

    Ying Chang +5

  6. cs.RO 2026-07-08 reviewed
    Fourier Decomposition Lets Robots Obey Speed Limits Without Bending Paths

    SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization

    Boxuan Zhang +3

  7. cs.LG 2026-07-08 reviewed
    Direct linear solves replace gradient steps in multi-input operator network training

    Hybrid Least Squares/Gradient Descent Methods for MIONets

    Jun Choi +2

  8. cs.CL 2026-07-08 reviewed
    LLMs can learn to reuse reasoning steps during deployment

    MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning

    Ruilin Tong +1

  9. cs.LG 2026-07-08 reviewed
    Simple text ensembles beat complex multimodal forecasters

    Rethinking Multimodal Time-Series Forecasting Evaluation

    Haoxin Liu +4

  10. cs.CV 2026-07-08 reviewed
    Representation, not prompt design, limits SAM in medical scans

    HPR-SAM: Hierarchical Probabilistic Representation Learning for Prompt-free SAM-based Medical Image Segmentation

    Yingzhen Hu +7

  11. eess.SY 2026-07-08 reviewed
    Networks Can Agree on Some Dimensions and Differ on Others

    Subspace Consensus of Matrix-Weighted Networks

    Yuhao Chen +4

  12. cs.RO 2026-07-08 reviewed
    LLM flight planner with memory and vision coach hits 94% validity

    End-to-End LLM Flight Planning with RAG-based Memory and Multi-modal Coach Agent

    Amin Tabrizian +5

  13. cs.CR 2026-07-08 reviewed
    Same AI that catches malware can now write it

    Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies

    Kiarash Ahi +1

  14. eess.SY 2026-07-08 reviewed
    Doubling data center load multiplies grid outage energy sevenfold

    Evaluating Grid Resilience in the Era of Ever-Increasing Data Centers

    Yuhan Du +2

  15. cs.RO 2026-07-08 reviewed
    Entropy regularizer keeps traffic simulators diverse

    Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation

    Seulbin Hwang +3

  16. cs.LG 2026-07-08 reviewed
    Step counts alone predict 21 health risks

    Physical activities enable scalable foundation modelling for broad-spectrum health prediction

    Zhenghuang Wu +2

  17. quant-ph 2026-07-08 reviewed
    Quantum search finds reset sequences in square-root time

    A quantum model for synchronizing finite state transition systems

    Martin Lukac +2

  18. cs.CV 2026-07-07 reviewed
    ELSA3D halves 3D model cost by routing text to the right scale

    ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

    Tianjiao Yu +6

  19. cs.RO 2026-07-07 reviewed
    3D-Lifted VLA Models Beat Prior Methods by 11% on Robot Tasks

    Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation

    Jiaming Liu +10

  20. cs.RO 2026-07-07 reviewed
    Floating Particles on Robots Render City Data in Mid-Air

    Embodied Human-Robot Interaction via Acoustics: A MARL Approach with AcoustoBots for Spatial Data Physicalization

    Shiqi Liu +4

  21. cs.CV 2026-07-07 reviewed
    One model, no task-specific heads, matches vision specialists

    Vision as Unified Multimodal Generation

    Xiaoyang Han +16

  22. cs.RO 2026-07-07 reviewed
    4D world model beats 2D policies on bimanual robot tasks

    RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

    Haoyu Zhao +5

  23. cs.CV 2026-07-07 reviewed
    Diffusion model tracks 6-DoF motion from video alone

    ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation

    Ruihang Zhang +4

  24. cs.CV 2026-07-07 reviewed
    Rewriting captions for infrared evidence lifts CLIP retrieval by up to 12.8 points

    MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation

    Jiaju Han +10

  25. cs.GT 2026-07-07 reviewed
    Quantum moves can't beat perfect classical play in board games

    Quantum combinatorial games

    Dieks Scholten +2

  26. cs.CV 2026-07-07 reviewed
    Style-transferred patches lift cross-site mammogram calcification AUC by 4-5 points

    Unsupervised Domain Adaptation for Calcification Classification in Mammography Across Multi-Site Datasets

    Xuan Liu +9

  27. cs.AI 2026-07-07 reviewed
    Oral Knowledge Could Counteract AI's Cultural Homogenization

    Rethinking Indic AI from a Lens of Cultural Heritage Preservation

    Aparna Madva +3

  28. cs.CL 2026-07-07 reviewed
    Chimp sequences so short even random parsers get 79% right

    On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other species?

    Ramon Ferrer-i-Cancho +3

  29. cs.CL 2026-07-07 reviewed
    Splitting deep layers lets spoken AI talk and think at once

    Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

    Zhenyu Liu +12

  30. cs.RO 2026-07-07 reviewed
    Zero-Shot MLLM Framework Solves Robot Last-Mile Navigation

    UniLM-Nav: A Unified Framework for Zero-Shot Last-Mile Navigation

    Zhuofan Zhang +8

  31. cs.RO 2026-07-07 reviewed
    Lipschitz Neural Net + Classical Observer = Provably Stable Robot Control

    Neural-ESO: A Dual-Pathway Architecture for Provably Robust Learning-Based Control

    Fan Zhang +6

  32. cs.CV 2026-07-07 reviewed
    Topology-aware attention lets 3D-LLMs reason across rooms

    CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

    He Liang +6

  33. math.NA 2026-07-07 reviewed
    Quantum-inspired classical solvers hit a wall on high-dimensional PDEs

    Quantum-inspired methods for finite-element discretizations of the high-dimensional Poisson equation

    Xue Wang +2

  34. cs.LG 2026-07-07 reviewed
    MILP generator keeps local blocks wired to their interfaces

    GraphBU: MILP Instance Generation with Graph-Native Block Units

    Xiaolei Guo +3

  35. cs.AI 2026-07-07 reviewed
    Swap any AI model, keep the same clinical routing

    The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology

    Ghassen Marrakchi +1

  36. cs.CL 2026-07-07 reviewed
    One Satellite Ratio Maps Neighborhood Wealth Across 59 Indian Cities

    Life Style Levels: Neighborhood Delineation using Geospatial Data

    Srivatsa Kulkarni +1

  37. cs.SI 2026-07-07 reviewed
    254x Citation Inflation Surfaced by Trust-Aware Graph Ranking

    Trust-Aware Citation Cartel Ranking in Scholarly Knowledge Graphs

    Pratyush Gupta +2

  38. cs.CL 2026-07-07 reviewed
    176M-parameter graph module matches 50-call LLM agents on KG question answering

    RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation

    Sambaran Bandyopadhyay +1

  39. cs.CR 2026-07-07 reviewed
    Threshold committee lets any chain's assets trade as ERC-20s

    Crossroads: A Smart Contract Layer for Chain-Abstracted Assets

    James Austgen +2

  40. math.AT 2026-07-07 reviewed
    No linear-size shortcut for Vietoris-Rips on rough spaces

    Lower Bounds for Approximating the Vietoris-Rips Filtration

    Kenneth McCabe

  41. cs.AI 2026-07-07 reviewed
    8.3x KV Cache Cut Holds Quality in Long-Context LLMs

    DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression

    Anna Cordoba +6

  42. cs.AI 2026-07-07 reviewed
    Grounding reasoning to physical outcomes lets 8B model beat expert

    Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment

    Han-Jun Ko +6

  43. quant-ph 2026-07-07 reviewed
    Quantum sensors can keep secrets and Heisenberg precision

    Differentially private quantum sensor networks

    Daniel J. Spencer +4

  44. cs.CV 2026-07-07 reviewed
    Point clouds stabilize closed-loop driving video generation

    Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation

    Songbur Wong +14

  45. cs.AI 2026-07-07 reviewed
    Fighting game stripped to rock-paper-scissors core becomes RL testbed

    FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

    Chase McDonald +2

  46. cs.HC 2026-07-07 reviewed
    Self-Powered Glasses Sensors Capture Pulse and Jaw Activity at 4 Microwatts

    GlassTENG: Self-Powered Triboelectric Nanogenerator based Sensing of Pulse, Jaw, and Upper Facial Activity from Everyday Glasses

    Raj N. Dave +7

  47. cs.CL 2026-07-07 reviewed
    Learned controller beats fixed pipelines for multi-hop evidence retrieval

    DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

    Yaqi Wu +9

  48. cs.SE 2026-07-07 reviewed
    GitHub repositories mapped to industry sectors at 97% precision

    Industry Classification of GitHub Repositories Using the North American Industry Classification System (NAICS)

    Kevin Xu +1

  49. cs.AI 2026-07-07 reviewed
    Real-world multivariate data beats synthetic for time-series models

    RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

    Qian Sun +4

  50. cs.AI 2026-07-07 reviewed
    Hidden states reveal doomed LLM agent episodes at round one

    Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

    Kai Ruan +5