CCXML
en.wikipedia.org·1d·
Discuss: Hacker News
🎙️Whisper
Building Git for Lawyers
theredline.versionstory.com·10h·
Discuss: Hacker News
🌿git
LongCat-Flash-Thinking, LLM from Meituan (China's Equivalent of Uber Eats)
github.com·16h·
Discuss: Hacker News
🌊Streaming Algorithms
Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
arxiv.org·20h
🌳Context free grammars
GPO: Learning from Critical Steps to Improve LLM Reasoning
arxiv.org·20h
✓Automated Theorem Proving
The Cutting-Edge DeFi Platform for 2025 – AI-Driven, Multi-Chain, and Secure
dev.to·16h·
Discuss: DEV
🖥️Self-hosted Infrastructure
Specification-Aware Machine Translation and Evaluation for Purpose Alignment
arxiv.org·20h
💻Programming languages
Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
arxiv.org·20h
🎙️Whisper
parSAT: Parallel Solving of Floating-Point Satisfiability
arxiv.org·20h
🧮SMT Solvers
CLaC at DISRPT 2025: Hierarchical Adapters for Cross-Framework Multi-lingual Discourse Relation Classification
arxiv.org·20h
📝Text Embeddings
Robustness of Neurosymbolic Reasoners on First-Order Logic Problems
arxiv.org·20h
🧮Prolog Parsing
Simplified Longitudinal Retrieval Experiments: A Case Study on Query Expansion and Document Boosting
arxiv.org·20h
🔍Information Retrieval
Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval
arxiv.org·20h
🔍Information Retrieval
ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding
arxiv.org·20h
🌀Brotli Internals
The Database Zoo: Inside Time-Series Engines (InfluxDB, Prometheus, Timescale)
hackernoon.com·22h
🗄️Database Internals
seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs
arxiv.org·20h
🔗Functional Compilers
Digging Into the Internal: Causality-Based Analysis of LLM Function Calling
arxiv.org·20h
🔗Functional Compilers
Evaluating CxG Generalisation in LLMs via Construction-Based NLI Fine Tuning
arxiv.org·20h
🤖Grammar Induction
Asking a Language Model for Diverse Responses
arxiv.org·20h
⚙️Compression Benchmarking
Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?
arxiv.org·20h
📝Text Parsing