Search: “llm”

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 se

arXiv:2607.12441v1 Announce Type: new Abstract: Wikipedia plays a key role in shaping public understanding of science, and its openly accessible revision history is a unique record of how scientific k

server : refactor prompt cache state ownership (#25649) server : clear checkpoints upon prompt clear server : move the prompt state data to the server_prompt_cache Assisted-by: pi:llama.cpp/Qwen3.6-27

cosign. models have overtuned to this now and do not realize when the agentsmd is out of date and should be changed/ignored. last night i goaled 5.6 sol to complete a 5 stage task and woke up to find

By the end of the year we should have: GPT 6 Fable 5.5 Gemini 3.5 Pro Grok 5 Spark 2 Kimi 3 Minimax M3.5 GLM 6 DeepSeek v4.5 Mistral 4 Qwen 4 MiMo 3 Never in the history of LLMs has the frontier been

Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without having use CLIs or open the browser? We built exactly that. Using @TauriAp ps, with a Rust backend power

We just shipped a full revamp of the RunAnywhere apps. iOS and Android, live now. One assistant, fully on-device, works offline: - new UI, opens straight into chat - device-aware model recommendations

Directly Responsible Individuals (DRI) I went looking for a definition of 'Directly Responsible Individuals' and the best I found was in the GitLab handbook. Apparently the term originated at Apple, w

One of the consequences of GPT-5.6 Sol being clearly a Fable/Mythos class model is that Anthropic have, once again, bumped the date that Fable stops being available in their Claude Max plans: We're ex

arXiv:2607.07974v1 Announce Type: cross Abstract: Intent detection is a critical task that bridges human intents and system actions in human-machine interaction systems. However, there still exist cha

arXiv:2607.07858v1 Announce Type: new Abstract: Artificial intelligence (AI) is beginning to reshape actuarial practice, particularly in domains that require reasoning over unstructured documents, het

b9948 is a build release of llama.cpp, an open-source C/C++ project for efficient large language model inference. The project ships continuous build-tagged releases using a build numbering system rath

arXiv:2607.08011v1 Announce Type: cross Abstract: Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these mode

arXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods m

arXiv:2607.07721v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) and agentic frameworks have advanced enterprise AI considerably, yet agents remain fundamentally reactive: they wai

arXiv:2607.07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents. Most public agentic coding benchmarks fo

arXiv:2607.08194v1 Announce Type: new Abstract: Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requi

arXiv:2504.07856v4 Announce Type: replace Abstract: Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dime

arXiv:2607.08288v1 Announce Type: cross Abstract: In critical infrastructure, operational technology environments often cannot be actively scanned, and yet active system feedback is needed for risk as

arXiv:2607.08086v1 Announce Type: new Abstract: Designing functional and aesthetically coherent floor plans requires exploring a vast space of possible room arrangements, a task that quickly becomes o

arXiv:2607.08346v1 Announce Type: new Abstract: Form 8-K filings are the primary channel through which U.S. public companies disclose material events, but the SEC item codes attached to them are coars

arXiv:2607.08448v1 Announce Type: new Abstract: Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end V

arXiv:2607.08758v1 Announce Type: new Abstract: Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biol

🚀langchain launches this week: all about open source models and memory! First: open source models. We partnered with @NVIDIAAI to launch a NemoClaw DeepAgents blueprint. This pairs Deep Agents (our op

arXiv:2607.08080v1 Announce Type: new Abstract: Aspect Sentiment Triplet Extraction (ASTE) requires jointly identifying (aspect, opinion, sentiment) triples from a given review sentence. While large l

One of my first journeys in neural networks started over a decade ago with implementing CPPN-NEAT! Back then, I built a clone of ‘Picbreeder’ not only to study the mechanics of neural nets, but to exp

arXiv:2407.09016v2 Announce Type: replace Abstract: Object-oriented embodied navigation tasks require agents to locate specific objects, either defined by category or images, in unseen environments. W

arXiv:2502.15543v4 Announce Type: replace-cross Abstract: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external ev

arXiv:2607.07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decompo

arXiv:2607.08269v1 Announce Type: new Abstract: Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We prese

arXiv:2607.08399v1 Announce Type: new Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant

arXiv:2607.08754v1 Announce Type: cross Abstract: Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization with

arXiv:2507.05240v2 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low

arXiv:2602.23440v4 Announce Type: replace Abstract: Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. How

arXiv:2607.08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. Ho

arXiv:2607.07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn? Today, the field largel

arXiv:2607.08312v1 Announce Type: new Abstract: How should language interface with a world model's discrete symbol system? The dominant paradigm -- end-to-end injection of LLM/VLM features into robot

arXiv:2607.08332v1 Announce Type: new Abstract: Financial markets are noisy, non-stationary, and high-dimensional, making it difficult to discover predictive and robust trading signals. Alpha discover

arXiv:2607.07527v1 Announce Type: cross Abstract: Artificial intelligence (AI) is a double-edged sword: while it has achieved remarkable success across a wide range of domains, its deployment also cal

arXiv:2607.07282v1 Announce Type: new Abstract: The Prasthanatrayi -- the ten principal Upanisads, the Brahmasutra, and the Bhagavadgita, with Sankara's commentaries (bhasya) -- is the foundational co

arXiv:2607.06624v1 Announce Type: new Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the ta

arXiv:2607.07601v1 Announce Type: cross Abstract: Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize co

arXiv:2508.17298v3 Announce Type: replace-cross Abstract: Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability t

arXiv:2604.25605v2 Announce Type: replace-cross Abstract: Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval

arXiv:2607.07021v1 Announce Type: new Abstract: Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms that act as shared tacit expec

Meta Platforms Inc. today launched a new flagship large language model optimized to power multi-agent automation workflows. Muse Spark 1.1 is available in the company’s Meta AI chatbot service and via