b10361
model : fix SWA not being enabled for EXAONE 4.5 (#26848) model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests hparams.n_layer() == 64 before LLM_KV_NEXTN_PREDICT_LAYERS has been r
Knowledge catalogue
model : fix SWA not being enabled for EXAONE 4.5 (#26848) model : fix SWA not being enabled for EXAONE 4.5 load_arch_hparams tests hparams.n_layer() == 64 before LLM_KV_NEXTN_PREDICT_LAYERS has been r
arXiv:2604.01653v2 Announce Type: replace Abstract: Electroencephalography (EEG) provides a non-invasive insight into the brain's cognitive and emotional dynamics. However, modeling how these states e
arXiv:2608.07494v1 Announce Type: cross Abstract: AI tools like ChatGPT and DeepSeek, powered by Large Language Models (LLMs), allow users to obtain instant and effective content responses simply by t
Lots of rumor and misinfo bouncing around, so I put some of these old mining cards to the test. I used 4 of the 8GB cards, set to 64GB each. Lots of models fit entirely on a single card, and you can a
arXiv:2608.09381v1 Announce Type: new Abstract: Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployme
arXiv:2608.08422v1 Announce Type: cross Abstract: Ranking data arise in scientific and machine learning applications, including recommendation systems, information retrieval, voting, marketing, and AI
arXiv:2608.08239v1 Announce Type: cross Abstract: LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents
arXiv:2608.08630v1 Announce Type: new Abstract: Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-atte
Anthropic: Anthropic details an unreleased Claude model's attempt to solve the Riemann hypothesis; it didn't solve it but “unexpectedly” made strides on a related problem — Recently, a member of staff
arXiv:2608.06434v1 Announce Type: cross Abstract: Embodied intelligence demands both long-horizon reasoning and real-time closed-loop responsiveness. Recent dual-system Vision-Language-Action (VLA) ar
the term “RLM” (recursive language model) got a lot of buzz this week, but this idea is not new! @a1zhang wrote the og RLM paper 10 months ago! thats like 5 agent-years! would highly recommend followi
Firstly a big thanks to the poster 'hellohazine', he basically only removed the multi-lingual fat of the model and just kept the English language intact. It is the exact model, and the rest of the mod
arXiv:2512.03057v2 Announce Type: replace-cross Abstract: We study distribution-free risk control for model routing, motivated by large language model reasoning. We formalize pointwise conditional eff
arXiv:2608.05642v1 Announce Type: new Abstract: This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its exp
arXiv:2507.14022v2 Announce Type: replace Abstract: This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis. The
arXiv:2608.05685v1 Announce Type: new Abstract: Most public benchmarks for machine-condition monitoring come from test rigs, where faults are induced on purpose and every event is known. Real producti
arXiv:2608.05389v1 Announce Type: new Abstract: Background: Accurate glioma subregion delineation is important for radiotherapy planning and longitudinal monitoring, but manual contour correction is t
arXiv:2608.05369v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in r
Looking for best current solutions for combining cloud models and local models seamlessly inside a harness' orchestration Edit: Right now, we don't have harnesses (that I'm aware of) that are blending
arXiv:2608.04433v1 Announce Type: cross Abstract: We present MERaLiON-GR, a speech gender recognition system that performs binary classification (female / male) on English and Southeast Asian (SEA) la
arXiv:2608.05076v1 Announce Type: cross Abstract: Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam p
Herb Scribner / Axios: OpenAI updates the default model for free users to GPT-5.6 Luna, adds unlimited text chats for free users, rolls out an improved GPT-5.6 Sol version, and more — OpenAI on Thursd
arXiv:2608.03990v1 Announce Type: new Abstract: Synthetic histopathology image generation has emerged as an approach that may address data scarcity in computational pathology, yet current evaluation m
arXiv:2608.03079v1 Announce Type: cross Abstract: Breast core needle biopsy (CNB) is central to breast cancer diagnosis yet remains challenging because limited tissue sampling, lesion heterogeneity, a
arXiv:2608.03599v1 Announce Type: new Abstract: Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a differe
arXiv:2604.04790v2 Announce Type: replace Abstract: Natural language processing (NLP) advances have powered a generation of LegalTech systems, but Turkish law remains under-served by domain-specific d
arXiv:2203.17257v2 Announce Type: replace Abstract: Salient Object Ranking (SOR) aims to estimate the relative saliency order among multiple salient objects. While SOR has been extensively studied in
arXiv:2608.03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but
arXiv:2608.03810v1 Announce Type: cross Abstract: Large language models routinely describe socially salient targets, including political figures, countries, religions, organizations, historical events
arXiv:2607.17244v2 Announce Type: replace Abstract: Longitudinal T cell receptor repertoires contain signals of clonal expansion, contraction, disappearance, and reappearance after immune perturbation
arXiv:2608.00697v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) trained on multiple sequence alignments (MSAs) have emerged as powerful generative models for biological sequences, wi
Mistral AI introduced Shieldstral, a 3‑billion‑parameter, open‑weights model designed for content‑safety tasks and capable of on‑device deployment. The announcement was shared via a tweet from @Mistra
Kimi K3 full model running on 16x GB10 cluster at 20+tps average (llama-benchy coherent corpus) 38tps peak, 750tps prefill. This is the first run of full k3 with dspark on my cluster. I will be doing
arXiv:2608.00989v1 Announce Type: cross Abstract: Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score.
arXiv:2608.00187v1 Announce Type: new Abstract: Correspondence-based statistical shape modeling (SSM) is vital for population-level morphometric analysis, but conventional pipelines assume clean, full
arXiv:2608.00725v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future observations. However, conditioning future prediction on
arXiv:2608.01397v1 Announce Type: cross Abstract: World Action Models (WAMs) couple action generation with prediction of future states. Their effectiveness depends on whether future dynamics are model
Today, we’re launching Alpamayo 2 Super, our frontier open reasoning model for autonomous vehicles. Beyond seeing, Alpamayo understands and reasons through the complex world - thinks before it acts. I
An internal version of our next major model produced 10 new results on long-standing open problems in mathematics and theoretical computer science, using roughly $2,000 worth of tokens at GPT-5.6 Sol
arXiv:2510.12953v4 Announce Type: replace-cross Abstract: Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are ada
// Model or Harness // Great paper if you are building with agents in production. (bookmark it) It organizes 41 agent failure modes by the interaction they originate in. Each mode gets assigned to an
arXiv:2607.29095v1 Announce Type: new Abstract: Accurate prediction of lithium-ion battery state of health (SOH) is essential for reliable energy storage operation. However, purely data-driven models
.@ssankar says Palantir was able to make Nvidia's Nemotron Ultra model 'better than frontier': 'I literally almost felt gaslit when, within 24 hours of getting Nemotron up with no post-training, this
arXiv:2607.28993v1 Announce Type: cross Abstract: World Action Models (WAMs) have emerged as a promising paradigm by jointly modeling robot actions and future visual dynamics. However, their reliance
arXiv:2607.29200v1 Announce Type: new Abstract: Ultrasound imaging has become increasingly widespread in clinical practice due to its portability, low cost and real-time capability, making ultrasound
As shocking as the Kimi K3 release. Massive performance gain was just with post-training Model is 3x smaller than GLM 5.2 (10x smaller than K3) & works on a MacBook / Spark This is Q1 flagship (Opus 4
arXiv:2508.16129v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities with reinforcement learning paradigm. Although se
https://preview.redd.it/h7zv5tb3tmgh1.png?width=2854&format=png&auto=webp&s=507380e8f862c18f10f7c5c84da9e8d1c59139b0 Deepseek's new flash model is unexpectedly cheap and high-performing across useful
Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our latest ASR model upgrades: • Context consistency • Domain-term recognition • Custom hotwords • Speech p
arXiv:2607.27450v1 Announce Type: new Abstract: Accurate multipath parameter estimation is critical for modern wireless communication systems, particularly in challenging low-SNR environments. Traditi
arXiv:2607.28415v1 Announce Type: cross Abstract: Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically
arXiv:2603.15684v2 Announce Type: replace-cross Abstract: Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although
At Google, AI is a soup-to-nuts endeavor. Obviously, we make leading AI models like Gemini and Nano Banana. We incorporate AI into the tools you use every day (think Gmail, BigQuery, AlloyDB, Google C
Okay, hear me out. Why is it that every time a new model comes out, all the tests I see are 'make a car game,' 'make a website,' or something equally generic, usually from a prompt that's barely a lin
arXiv:2607.26196v1 Announce Type: new Abstract: Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet exis
arXiv:2607.25156v1 Announce Type: new Abstract: Structure-prediction networks built on co-evolutionary statistics have transformed protein-based drug discovery, yet their accuracy does not extend to p
arXiv:2602.10508v2 Announce Type: replace Abstract: Modern segmentation models achieve strong predictive performance but remain largely opaque, limiting our ability to diagnose failures, understand da
arXiv:2607.25366v1 Announce Type: cross Abstract: LLM-based Cross-Domain Sequential Recommendation (CDSR) leverages LLMs to enhance target performance via deep semantic reasoning, alleviating the depe
Multiverse Computing SL, a startup working on technology that compresses artificial intelligence models so that they run more efficiently on less hardware, announced Monday it raised 570 million in Se
arXiv:2607.23289v1 Announce Type: cross Abstract: Gene regulatory network modeling often requires balancing predictive accuracy and mechanistic interpretability. In this work, we compare continuous su