Skip to content
Papers.
Updated 12h ago

Research papers

40 papers from 15 labs, newest first. Sort by citations or Hugging Face upvotes under Filters.

40 of 40 papers, newest first

PaperCitations
RRSI: Regularized Recursive Self-Improvement of Agent HarnessesRRSI keeps self-improving agent harnesses from memorising their training tasks, so gains carry over to new benchmarks.Google · Sep 20260
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache CompressionA 552B mixture-of-experts model with a 1M-token context, built to shrink the KV cache for agent workloads.DeepSeek · Sep 20267
StudentSim: Training LLM-based Student SimulatorsStudentSim trains per-student simulators that answer like a given learner and change their answers under a tutor's guidance.Microsoft · Sep 20260
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training StabilityQwen3.8-Flash-Next: a 125B mixture-of-experts model with 6B active that nearly matches its 397B predecessor at 1/9 the training compute.Alibaba (Qwen) · Aug 20266
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and RecipesControlled experiments on when text, image understanding and image generation help or compete when trained together.Meta · Aug 20262
Gemma 4 Technical ReportOpen multimodal models from 2.3B to 31B parameters, with a thinking mode and image and audio input.Google DeepMind · Jul 2026106
Agents' Last ExamOver 1,000 real, checkable professional tasks written with 250+ industry experts; the hardest tier is far from solved.UC Berkeley · Jun 202615
Cosmos 3: Omnimodal World Models for Physical AIOne model that reads and generates text, images, video, audio and robot actions for physical AI.NVIDIA · Jun 202690
MolmoAct2: Action Reasoning Models for Real-world DeploymentA fully open robot action model, released with new datasets including 720 hours of two-arm teleoperation.Ai2 · May 202644
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document CollectionsOn 2,250 questions over 800 PDFs, the best agents match human accuracy but lean on brute-force search rather than planning.Snowflake · Mar 20261
Why Language Models HallucinateModels hallucinate because training and benchmarks reward confident guessing over saying they do not know.OpenAI · Sep 2025329
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingClassifiers trained from a written constitution held off universal jailbreaks through more than 3,000 hours of red teaming.Anthropic · Jan 2025199
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningReinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.DeepSeek · Jan 20255,691
Alignment faking in large language modelsClaude 3 Opus sometimes went along with a training goal it disagreed with, to avoid being changed, without being told to.Anthropic · Dec 2024342
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model TransformationSwiftKV lets prompt tokens skip later layers and merges KV caches, cutting prefill cost for long-prompt workloads.Snowflake · Oct 202418
The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta · Jul 202418.8k
Nemotron-4 340B Technical ReportOpen models sized for one 8-GPU server, aligned with over 98% synthetic data.NVIDIA · Jun 2024138
LoRA Learns Less and Forgets LessLoRA learns less than full fine-tuning on code and math, but forgets less of what the model already knew.Databricks · May 2024405
Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding ModelsOpen text embedding models from 22M to 334M parameters that led MTEB retrieval for their size at release.Snowflake · May 202480
From Local to Global: A Graph RAG Approach to Query-Focused SummarizationGraphRAG builds a knowledge graph of a document set so a model can answer questions about the whole collection.Microsoft · Apr 20242,191
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your PhoneSmall models trained on filtered and synthetic data that run on a phone and rival much larger ones.Microsoft · Apr 20242,497
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextRecalls details across millions of tokens of text, hours of video and days of audio.Google DeepMind · Mar 20244,002
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.Anthropic · Jan 2024576
Mamba: Linear-Time Sequence Modeling with Selective State SpacesA selective state space model that scales linearly with sequence length and matches Transformers on language.Carnegie Mellon University · Dec 20239,182
Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.UC Berkeley · Sep 20238,469
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelDPO aligns a model to human preferences with a simple classification loss, no reward model or RL loop.Stanford University · May 202310.6k
Segment AnythingA promptable model and a dataset of over a billion masks that cut out any object in any image.Meta · Apr 202315.7k
GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI · Mar 202327.3k
LLaMA: 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.Meta · Feb 202321.7k
Constitutional AI: Harmlessness from AI FeedbackConstitutional AI trains a harmless assistant from AI feedback guided by a short list of written principles, not human harm labels.Anthropic · Dec 20223,718
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.Stanford University · May 20225,331
Training Compute-Optimal Large Language ModelsChinchilla: for a fixed compute budget, train a smaller model on more data; parameters and tokens should grow together.Google DeepMind · Mar 20223,755
Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.OpenAI · Mar 202224.2k
Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.Google · Jan 202222.1k
LoRA: Low-Rank Adaptation of Large Language ModelsLoRA fine-tunes a large model by training small low-rank matrices, cutting trainable parameters by 10,000 times.Microsoft · Jun 202123.2k
Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI · May 202063.6k
Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.OpenAI · Jan 20209,061
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismMegatron-LM splits each Transformer layer across GPUs to train models with billions of parameters.NVIDIA · Sep 20193,177
BERT: 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.Google · Oct 2018121k
Attention Is All You NeedIntroduced the Transformer, the attention-only architecture behind nearly every large language model since.Google · Jun 2017194k

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.