Search: “model-releases”

arXiv:2604.07429v1 Announce Type: new Abstract: Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse f

Gen Z is increasingly disillusioned with AI - just not enough to stop using it. A new Gallup report released this week, based on responses from nearly 1,600 people ages 14 to 29 across the US, suggest

arXiv:2412.19685v2 Announce Type: replace-cross Abstract: Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insi

GLM-5.1 by @Zai_org is now #3 in Code Arena - surpassing Gemini 3.1 and GPT-5.4, and now on par with Claude Sonnet 4.6. The first frontier level open model to break into the top 3. It’s a major +90 po

arXiv:2604.08131v1 Announce Type: new Abstract: The rapid spread of online misinformation has led to increasingly complex detection models, including large language models and hybrid architectures. Ho

arXiv:2604.07808v1 Announce Type: new Abstract: Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this cha

Grok 4.20 hitting 83% on non-hallucination. Values truth. Claude ~74%. Others sitting in the 60s… or way lower. Less guessing. More honesty when it doesn’t know. That’s a different kind of intelligenc

arXiv:2603.01059v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have enabled increasingly capable chatbots. However, most existing systems focus on single-user sett

arXiv:2604.06358v1 Announce Type: cross Abstract: Exploring ensemble simulations is increasingly important across many scientific domains. However, supporting flexible post-hoc exploration remains cha

haha cool, this worked. an MCP server that allows Claude to build it's own reusable skills https://github.com/yoheinakajima/selfMCP (1473 LoC) basically a server with skills to CRUD skills in this vid

arXiv:2604.06191v1 Announce Type: cross Abstract: Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain sca

Help us grow our list of community middlewares! https://docs.langchain.com/oss/python/integrations/middleware#community-integrations @IeloEmanuele is on a roll! you can now use claude code's advisor s

arXiv:2603.20843v2 Announce Type: replace Abstract: Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring r

arXiv:2604.06845v1 Announce Type: cross Abstract: Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely

arXiv:2604.08305v1 Announce Type: cross Abstract: Immunohistochemistry (IHC) is essential for assessing specific immune biomarkers like Human Epidermal growth-factor Receptor 2 (HER2) in breast cancer

arXiv:2604.06614v1 Announce Type: cross Abstract: Prompt learning has gained significant attention as a parameter-efficient approach for adapting large pre-trained vision-language models to downstream

For decades, expense automation relied on a simple premise: If the machine can read the text, it can do the work. But anyone who has ever tried to scan a crumpled, smudged, or sun-bleached receipt fro

arXiv:2604.07430v1 Announce Type: new Abstract: We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Visi

arXiv:2604.08256v1 Announce Type: new Abstract: Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across exte

I strongly suspect that Claude Mythos is a looped language model, as described in the paper 'Scaling Latent Reasoning via Looped Language Models' from ByteDance The authors of that paper called out gr

arXiv:2604.07709v1 Announce Type: cross Abstract: Ask a frontier model how to taper six milligrams of alprazolam (psychiatrist retired, ten days of pills left, abrupt cessation causes seizures) and it

@IeloEmanuele is on a roll! you can now use claude code's advisor strategy with @LangChain agents because langchain/deepagents are provider agnostic, you can use different providers for your advisor a

if it creates a skill, and it errors, it will (at least sometimes) just try to fix it. what’s cool is that all the web search and code writing is offloaded to Claude (or whatever chat you’re using), a

If you want to see the setup... https://x.com/alliekmiller/status/2042728780847047131?s=20 So many people wanted to see my knowledge management system in Claude code, so here it is. All you need is Ob

arXiv:2604.06211v1 Announce Type: cross Abstract: Natural language explanations produced by large language models (LLMs) are often persuasive, but not necessarily scrutable: users cannot easily verify

In a world where writing code to build websites and apps is trivial (thank you Lovable, Cursor, Claude,...), the real differentiation for you and your company (and what makes you successful) will be h

arXiv:2508.13657v2 Announce Type: replace-cross Abstract: Combined Algorithm Selection and Hyperparameter Optimization (CASH) has been fundamental to traditional AutoML systems. However, with the adva

arXiv:2604.07108v1 Announce Type: cross Abstract: Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existi

arXiv:2602.09987v5 Announce Type: replace-cross Abstract: Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that i

arXiv:2604.08118v1 Announce Type: new Abstract: Additive quantization enables extreme LLM compression with O(1) lookup-table dequantization, making it attractive for edge deployment. Yet at 2-bit prec

arXiv:2604.06796v1 Announce Type: cross Abstract: Latent variable models, including variational autoencoders (VAE), remain a central tool in modern deep generative modeling due to their scalability an

arXiv:2604.08337v1 Announce Type: new Abstract: Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only s

arXiv:2604.06213v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at human-like language generation but often embed and amplify implicit, intersectional biases, especially under per

arXiv:2604.03044v2 Announce Type: replace-cross Abstract: We introduce JoyAI-LLM Flash, an efficient Mixture-of-Experts (MoE) language model designed to redefine the trade-off between strong performan

arXiv:2604.03815v2 Announce Type: replace-cross Abstract: Graph transformers have shown promise in overcoming limitations of traditional graph neural networks, such as oversquashing and difficulties i

arXiv:2604.07240v1 Announce Type: cross Abstract: We introduce a code-based challenge for automated, open-ended mathematical discovery based on the k-server conjecture, a central open problem in com

arXiv:2604.07969v1 Announce Type: new Abstract: We present Kathleen, a text classification architecture that operates directly on raw UTF-8 bytes using frequency-domain processing -- requiring no toke

arXiv:2510.05524v2 Announce Type: replace Abstract: We present Knowledge Extraction on OMIn (KEO), a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in s

arXiv:2604.07034v1 Announce Type: cross Abstract: We present KITE, a training-free, keyframe-anchored, layout-grounded front-end that converts long robot-execution videos into compact, interpretable t

arXiv:2511.10354v1 Announce Type: cross Abstract: Cultural Heritage texts contain rich knowledge that is difficult to query systematically due to the challenges of converting unstructured discourse in

arXiv:2604.07904v1 Announce Type: cross Abstract: Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized t

arXiv:2604.08426v1 Announce Type: cross Abstract: With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both

La France a parmi les meilleurs mathématiciens et ingénieurs IA du monde. On le sait. On les embauche partout ailleurs. Et la première chose qu'on fait au moment où on pourrait enfin capitaliser dessu

arXiv:2604.06438v1 Announce Type: cross Abstract: Forecasters often choose retraining schedules by convention rather than by an explicit decision rule. This paper gives that decision a posterior-space

arXiv:2604.06255v1 Announce Type: cross Abstract: Stellar astrophysics relies critically on accurate descriptions of the physical conditions inside stars. Traditional solvers such as exttt{MESA} (Mo

arXiv:2509.17183v3 Announce Type: replace-cross Abstract: Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional align