Your daily digest
Research papers, made simple to understand
The AI and machine learning papers people are reading most, each one rewritten in plain words: the problem, the idea, what was found and why it matters.
- AI Agents
- Language Models & Architectures
Xing 4 advances large language models on Ascend chips with efficient architecture and training
Xing 4 models optimize architecture and training on Ascend NPUs, achieving efficient long-context reasoning and agentic tasks with a 285B-parameter model pretrained on 8,192 Ascend 910C cards and a 29B open-source MoE model supporting 256K-token contexts.
Paper: TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks · Xingchen AGI Lab, Baotian Hu, Bingkai Yang and 136 others
150 upvotes on Hugging Face6 min readRead the article
- AI Agents
- Benchmarks & Evaluation
AscendGYM benchmarks kernel optimization on Ascend NPUs with cost-aware metrics
AscendGYM evaluates agents' ability to optimize existing Ascend NPU kernels from real LLM workloads, using a new Speedup-Token Score metric that balances performance gains with token cost under budget constraints.
Paper: AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs · AI Training Platform Team, Bingwei Zhang, Jing Li and 24 others
91 upvotes on Hugging Face7 min readRead the article
- Language Models & Architectures
LLMs design sparse table models outperforming Transformers in weight-space programming
Large language models (LLMs) writing weights directly without gradient training prefer sparse associative-memory tables over Transformers, achieving up to 54.4% accuracy on ARC with 1,800× fewer parameters and up to 17× faster inference on GPUs.
Paper: Weight-Space Programming Doesn't Need Transformers · Hyunjong Ok, Jaeho Lee
49 upvotes on Hugging Face5 min readRead the article
Browse earlier papers
18 days of papers in November 2026
- WeVisForensics jointly trains an investigator agent and evolving forensic inspectors for AI video detectionand 2 more papers
- Jeveration generates images and dense predictions in one fast forward passand 2 more papers
- Xing 4 advances large language models on Ascend chips with efficient architecture and trainingYou are reading this day
- Sage S2.1 Flash: A 320B-parameter multimodal model excelling in scientific reasoning and agentic tasksand 2 more papers
- Agentic robotics uses foundation models plus harnesses for versatile physical task controland 2 more papers
- Direct Preference Optimization fine-tunes language models from human preferences without reinforcement learningand 2 more papers
- Layer normalization stabilizes and speeds up training, especially in recurrent networksand 2 more papers
- SO-Arena benchmarks System One models' decision capabilities and reliability across domainsand 2 more papers
- Structured textbook-based supervision improves mathematical reasoning in large language modelsand 2 more papers
- Tree-Ising optimizes sparse bit-level edits to fix reasoning loops in language modelsand 2 more papers
- Unified tactile representation improves dexterous robot manipulation across sensor typesand 2 more papers
- Gaussian Spacing Normalization improves feed-forward 3D Gaussian Splatting generalizationand 2 more papers
- VFlash enables fast, accurate visual plan decoding by jointly predicting entire primitivesand 2 more papers
- TurnWise improves streaming video RL by assigning credit at each decision turnand 1 more paper
- Routing specialized AI models boosts efficiency and performance across tasksand 2 more papers
- Unified taxonomy and literature system organize agentic computer graphics researchand 2 more papers
- FrameForge adapts video models for diverse conditional image generation with input-adaptive temporal relationsand 2 more papers
- Diffusion models generate high-quality images by learning to reverse noise additionand 2 more papers