Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Embarrassingly Simple Self-Distillation Improves Code Generation research paper by Apple, 2026

Apple · Foundation models · Apr 1, 2026 · 40 citations · 55 upvotes · unverified

Read on arXiv

What it shows

Simple self-distillation improves code generation in large language models by fine-tuning on model-generated samples, effectively addressing precision-exploration trade-offs in decoding.

By Ruixiang Zhang, Richard He Bai, Huangjie Zheng and 3 more · arXiv 2604.01193 · PDF · Code

UnverifiedHugging Face's summary; not yet checked by hand.

More from Apple

All 11
Multimodal and roboticsUnverifiedOct 19, 2026OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal MemoryThis framework improves multimodal AI reasoning by providing persistent memory and tool interfaces to help models process and combine complex visual evidence.Apple101 upvotesRead →Inference and efficiencyUnverifiedOct 1, 2026Decoding Looped Transformers Better for (Almost) FreeLoopCD improves decoding quality in looped transformers by contrasting final predictions with earlier recurrent states without extra training.Apple1 citations46 upvotesRead →Multimodal and roboticsUnverifiedSep 18, 2026MintAct: A Unified Visual Agent for Digital EnvironmentsMintAct is a unified vision-language model family that handles UI grounding and multi-step navigation across various digital environments.Apple35 upvotesRead →Retrieval and dataUnverifiedSep 1, 2026It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement LearningCoGR trains LLMs to generate compact keywords for both queries and items, enabling direct inverted-index retrieval optimized via co-evolving reinforcement learning.Apple2 citations65 upvotesRead →ReasoningUnverifiedMar 1, 2026CHIMERA: Compact Synthetic Data for Generalizable LLM ReasoningA synthetic reasoning dataset called CHIMERA is introduced to overcome data-centric challenges in training large language models for cross-domain reasoning, achieving performance comparable to much larger models.Apple2 citations57 upvotesRead →Multimodal and roboticsUnverifiedDec 11, 2025Sharp Monocular View Synthesis in Less Than a SecondSHARP synthesizes photorealistic views from a single image using a 3D Gaussian representation, achieving state-of-the-art results with rapid processing.Apple32 citations31 upvotesRead →Multimodal and roboticsUnverifiedDec 8, 2025One Layer Is Enough: Adapting Pretrained Visual Encoders for Image GenerationFAE, a framework using a feature auto-encoder and dual decoders, adapts pre-trained visual representations for generative models, achieving high performance in image generation tasks.Apple32 citations25 upvotesRead →Multimodal and roboticsUnverifiedNov 25, 2025STARFlow-V: End-to-End Video Generative Modeling with Normalizing FlowSTARFlow-V, a normalizing flow-based video generator, offers end-to-end learning, robust causal prediction, and high-quality video generation with practical sampling efficiency.Apple8 citations33 upvotesRead →

Other foundation models papers

Topic
Foundation modelsOct 11, 2018BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google125k citations33 upvotesRead →Foundation modelsMay 28, 2020Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI66.4k citations21 upvotesRead →Foundation modelsMar 15, 2023GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI28.4k citations7 upvotesRead →Foundation modelsFeb 27, 2023LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta22.6k citations25 upvotesRead →Foundation modelsJul 31, 2024The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta20.8k citations119 upvotesRead →Foundation modelsUnverifiedMay 14, 2025Qwen3 Technical ReportQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen)10.1k citations339 upvotesRead →
About this paper
Venue
arXiv.org
Citations
40, 3 influential · Semantic Scholar
Upvotes
55 · Hugging Face
Lab
Apple · on Companies · on Quarterly · on Paydays · on TechConf

Changes

CitationsNov 9, 2026Citations rose from 39 to 40.
CitationsNov 2, 2026Citations rose from 36 to 39.
CitationsOct 12, 2026Influential citations rose from 2 to 3.
CitationsOct 12, 2026Citations rose from 34 to 36.
CitationsOct 5, 2026Citations rose from 33 to 34.
CitationsSep 25, 2026A first count of 2 influential citations.
CitationsSep 25, 2026A first count of 33 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.