Paper Reviews by AI

M3-AGIQA: A multimodal AI solution that comprehensively assesses AI-generated image quality, achieving state-of-the-art performance by distilling online MLLM capabilities into a local model.

LightThinker: LLMs dynamically compress intermediate steps, reducing memory & boosting reasoning efficiency without sacrificing accuracy.

Predicting open-weight AI model growth on Hugging Face using a citation-style model, revealing adoption dynamics and influencing factors.

KoNET: Evaluating multimodal AI in Korean with edu standards.

UPCORE reduces unintended unlearning effects via coreset selection, balancing knowledge removal and utility preservation.

LLMs struggle with positional bias and lack transparency when summarizing long contexts. This paper introduces SUnsET dataset and fine-tuning methods to improve unstructured evidence citation and summ…

SURVEYX automates academic survey generation, enhancing content and citation quality.

Current LLM evaluation benchmarks often overlook the structural dependencies in multi-turn dialogues, treating them as simple concatenations of single-turn interactions. This approach neglects user in…

SigLIP 2: Multilingual Vision-Language Encoders with Semantic Understanding, Localization, and Dense Features.

CoSyn: Code-guided synth data for scaling text-rich image understanding, achieving SOTA via targeted multimodal data generation!

S*: Hybrid test-time scaling for code generation, boosting both coverage and selection accuracy.

ReQFlow: Efficiently generate high-quality protein backbones with rectified quaternion flow, outperforming existing methods in speed and designability.

RelaCtrl: Relevance-guided control boosts diffusion transformer efficiency, cutting parameters by intelligently allocating resources.

PhotoDoodle: Mimicking artistic image editing with personalized decorative elements through learning from few-shot pairwise data.

PC-Agent: A new hierarchical framework that significantly improves complex task automation on PCs by 32%!

MLGYM: A new framework & benchmark to advance AI Research Agents

Logic-RL unlocks LLM reasoning via rule-based reinforcement learning, generalizing to math problems after training on logic puzzles.

LLMs use punctuation in context memory, surprisingly boosting performance by using seemingly trivial tokens.

PURE: LLM-driven user profile management boosts recommendation by harnessing user reviews for personalized insights while tackling token limits. PURE enhances LLMs for better recommendations.

KITAB-Bench: A new multi-domain Arabic OCR benchmark to bridge the performance gap with English OCR technologies.