Stay updated with the latest in AI models. Here are the top picks for today, curated and summarized by HappyMonkey AI.
LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
Computer Science > Computer Vision and Pattern Recognition Title: LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4 Submission history Access Paper: View PDF HTML (experimental) TeX Source…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs
Computer Science > Computation and Language Title: VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context: References & Citations NASA ADS Google Scholar…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching
Computer Science > Machine Learning Title: Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context: References & Citations NASA ADS Google Scholar Semantic Scholar…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models
Computer Science > Computation and Language Title: Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context: References & Citations NASA ADS Google Scholar Semantic…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
DrawingVQA: A Real-World Benchmark for Multi-Depth Visual-Textual Reasoning on Construction Drawings
Computer Science > Artificial Intelligence Title: DrawingVQA: A Real-World Benchmark for Multi-Depth Visual-Textual Reasoning on Construction Drawings Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context: References & Citations NASA…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery
Computer Science > Computation and Language Title: Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context: References & Citations NASA ADS Google Scholar Semantic…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?
Computer Science > Artificial Intelligence Title: Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?. Submission history Access Paper: View PDF TeX Source Current browse context: References & Citations NASA ADS Google Scholar…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning
Computer Science > Computation and Language Title: Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context:…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data
Computer Science > Artificial Intelligence Title: CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context: References & Citations NASA…
Why it matters: Potentially relevant AI tooling update — review for integration potential.
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
Computer Science > Computation and Language Title: RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization Submission history Access Paper: View PDF HTML (experimental) TeX Source Current browse context:…
Why it matters: Potentially relevant AI tooling update — review for integration potential.