๐ŸŽ“How I Study AIHISA
๐Ÿ“–Read
๐Ÿ“„Papers๐Ÿ“ฐBlogs๐ŸŽฌCourses
๐Ÿ’กLearn
๐Ÿ›ค๏ธPaths๐Ÿ“šTopics๐Ÿ’กConcepts๐ŸŽดShorts
๐ŸŽฏPractice
๐Ÿ“Daily Log๐ŸŽฏPrompts๐Ÿง Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Papers4

AllBeginnerIntermediateAdvanced
All SourcesarXiv
#inference-time scaling

RelayGen: Intra-Generation Model Switching for Efficient Reasoning

Intermediate
Jiwon Song, Yoongon Kim et al.Feb 6arXiv

RelayGen is a training-free way to switch between a big model and a small model while one answer is being generated.

#RelayGen#intra-generation model switching#segment-level routing

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

Intermediate
Ziwei Luo, Ziqi Jin et al.Feb 2arXiv

The paper introduces a new way to sample text from masked diffusion language models that is smarter and less greedy.

#masked diffusion language models#sequential Monte Carlo#self-rewarding sampling

TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models

Beginner
Fangxu Yu, Xingang Guo et al.Jan 26arXiv

TSRBench is a giant test that checks if AI models can understand and reason about data that changes over time, like heartbeats, stock prices, and weather.

#time series reasoning#multimodal benchmark#perception

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey

Beginner
Caihua Li, Lianghong Guo et al.Jan 15arXiv

This paper is the first big map of how AI can fix real software problems, not just write short code snippets.

#SWE-bench#issue resolution#AI coding agents