cs.SE

Papers

• Type4Py: Practical Deep Similarity Learning-Based Type Inference for Python (2022)
  Amir M. Mir et al.
  —
• Deterministic Iteratively Built KD-Tree with KNN Search for Exact Applications (2021)
  Aryan Naim et al.
  —
• Identical Image Retrieval using Deep Learning (2022)
  Sayan Nath et al.
  —
• Querying Spatial-Temporal-Spectral Data Using a Graphical Query Builder (2022)
  Adela Gorczynska et al.
  —
• Searching, fast and slow, through product catalogs (2024)
  Dayananda Ubrangala et al.
  —
• Embedding-based search in JetBrains IDEs (2024)
  Evgeny Abramov and Nikolai Palchikov
  —
• Synthesizing Document Database Queries using Collection Abstractions (2024)
  Qikang Liu et al.
  —
• Polygon: Symbolic Reasoning for SQL using Conflict-Driven Under-Approximation Search (2025)
  Pinhan Zhao et al.
  —
• ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (2026)
  Peng Ding et al.
  —
• Which Is Better For Reducing Outdated and Vulnerable Dependencies: Pinning or Floating? (2026)
  Imranur Rahman et al.
  —
• Vextra: A Unified Middleware Abstraction for Heterogeneous Vector Database Systems (2026)
  Chandan Suri et al.
  —
• HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench (2026)
  Yueyang Wang et al.
  —
• MedBeads: An Agent-Native, Immutable Data Substrate for Trustworthy Medical AI (2026)
  Takahito Nakajima
  —
• Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems (2026)
  Samaresh Kumar Singh et al.
  —
• static_maps: consteval std::map and std::unordered_map Implementations in C++23 (2026)
  Isaac D. Myhal et al.
  —
• SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution (2026)
  Kang He et al.
  —
• Tool Calling is Linearly Readable and Steerable in Language Models (2026)
  Zekun Wu (University College London) et al.
  —
• CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging (2026)
  Shiyang Li et al.
  —
• AgentAtlas: Beyond Outcome Leaderboards for LLM Agents (2026)
  Parsa Mazaheri et al.
  —
• The Neglected Baseline in Model Interpretation (2026)
  Yongjin Cui et al.
  —
• GazeBehavior Annotation Toolkit (GBAT): AI-powered toolkit for automatic annotation of egocentric eye-tracking and video data of child-caregiver interaction (2026)
  Iba Baig et al.
  —
• Finding Performance Issues in Database Systems by Exploiting Dormant Code Paths (2026)
  Jinsheng Ba et al.
  —
• Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents (2026)
  Yuandao Cai et al.
  —
• LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs (2026)
  Zenghui Zhou et al.
  —
• CAFD: Concept-Aware DNN Fault Detection using VLMs (2026)
  Amin Abbasishahkoo et al.
  —
• The Time is Here for Just-in-Time Systems: Challenges and Opportunities (2026)
  Shu Liu et al.
  —
• Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild (2026)
  Zhimin Zhao et al.
  —
• AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Systems (2026)
  Petar Radanliev
  —
• TRACE: A taxonomy-grounded synthetic dataset for teaching-program generation and session interpretation in Applied Behavior Analysis (2026)
  Festus Kahunla
  —
• When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges (2026)
  Parth Darshan et al.
  —
• The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models (2026)
  Jaideep Ray
  —
• VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents (2026)
  JunJia Guo (Joe) et al.
  —
• SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup? (2026)
  Zihang Zhou et al.
  —
• Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification (2026)
  Jingxi Qiu et al.
  —
• EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering (2026)
  Zhifei Dou et al.
  —