Knowledge catalogue
arXiv:2609.17940v1 Announce Type: new Abstract: Sparse mixture-of-experts models route each token through a sequence of expert selections. We ask whether the immediately preceding selection adequately
Yoyo I renamed https://github.com/syv-ai/qwen38-27b-rtx3090 to https://github.com/syv-ai/HyperQwen/ to focus more on Qwen models and 'local' hardware in general, than just a single card and a single m
arXiv:2609.18996v1 Announce Type: new Abstract: LLM agents have repeatedly struggled to convert knowledge of a game into competent play, even when researchers build the agent around the model - supply
arXiv:2603.03884v2 Announce Type: replace-cross Abstract: Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introdu
arXiv:2609.18080v1 Announce Type: new Abstract: Linear probes can decode safety-relevant concepts such as truthfulness from language-model activations, but probe accuracy may show only decodability, n
arXiv:2609.18374v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models attach an action module to a Vision-Language Model (VLM) with billions of parameters and pay for that backbone at ev
deepseek v4.1 flash on together ai is leading on ttft for pre-warmed queries for agent workflows, that startup time shows up again on every model turn, so shaving it down matters more as the loop gets
arXiv:2609.18444v1 Announce Type: new Abstract: Weakly supervised class-incremental semantic segmentation (WILSS) aims to train a segmentation model over multiple steps, each introducing new concepts
arXiv:2609.18465v1 Announce Type: new Abstract: Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low par
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these
Editor's note: Lucius AI, a tender-intelligence startup covering markets across five continents, runs its entire data platform on AlloyDB for PostgreSQL with a single operator. By migrating semantic s
We compared 20 model versions on 360 frozen joke prompts, with four jokes requested per prompt and model names hidden from our humor-trained judge. Fable 5 had the highest estimated score: 66.8 points
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy rece
arXiv:2609.18578v1 Announce Type: new Abstract: Pathologists diagnose diseases by first locating suspicious tissue and then examining it at higher magnification, whereas self-supervised vision transfo
arXiv:2609.18357v1 Announce Type: new Abstract: Large language model (LLM) pricing agents may respond to how market data is presented, even when its numerical values remain unchanged. We introduce mar
arXiv:2609.18315v1 Announce Type: new Abstract: Non-intrusive load monitoring (NILM) estimates appliance power sequences from aggregate power, but models trained on source households commonly lose acc
arXiv:2609.19145v1 Announce Type: cross Abstract: Two dominant tokenisation algorithms are used by modern language models: byte-pair encoding (BPE) and UnigramLM. These differ along two orthogonal axe
Hello, I'm at the old pro plan. With the upcoming cloud model retirement of deepseek v4 0731 flash in mind because 4.1 is supposed to be more efficient while providing even better results I remembered
OpenAI: OpenAI launches Astra for Law, combining GPT-6 Astra with a legal search index and instructions for legal analysis and writing, initially for select law firms — Our most powerful model, config
arXiv:2609.18863v1 Announce Type: new Abstract: Reliable prediction of crystallographic texture in laser powder bed fusion is critical for linking process conditions with anisotropic response and for
arXiv:2609.18049v1 Announce Type: new Abstract: Model explainability is essential for understanding and trusting machine learning models. Existing explainable AI methods often explain predictions thro
arXiv:2609.18207v1 Announce Type: cross Abstract: Reinforcement learning fine-tuning on top of large, pretrained Vision-Language-Action (VLA) models offers promise for highly reliable robot deployment
arXiv:2609.17745v1 Announce Type: cross Abstract: A central goal of autonomous reinforcement learning is continuous policy training without external resets. However, existing paradigms largely depend
arXiv:2503.10265v3 Announce Type: replace Abstract: Robotic-assisted surgery (RAS) is central to modern surgery, driving the need for intelligent systems with accurate scene understanding. Most existi
arXiv:2609.18194v1 Announce Type: new Abstract: In Taiwanese Hokkien automatic speech recognition (ASR), prior studies often treat tone sandhi as a major challenge under the assumption that models fai
🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-w
Today, we’re announcing Ternary Bonsai 2 27B. Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance. Two mon
Two weeks. That's how long it took to go from GLM-5.3-Flash's first run on domestic accelerators to serving all of its production traffic, with 3.2× end-to-end throughput along the way. What I keep th
arXiv:2508.11584v3 Announce Type: replace-cross Abstract: Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant
arXiv:2606.15121v3 Announce Type: replace Abstract: Predicting the timing of individual and collective panic emotional arousal before manifestation is essential for timely emergency intervention. Exis
arXiv:2609.18731v1 Announce Type: new Abstract: Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal languages like P
arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with
arXiv:2609.16573v1 Announce Type: new Abstract: Multi-modal spatio-temporal forecasting (MM-STF) supports weather nowcasting, traffic prediction, and earth-system modeling by combining heterogeneous s
arXiv:2501.09166v2 Announce Type: replace-cross Abstract: Pretrained Transformers keep what they learned in their weights and lose what they observe once a session ends. The first version of this pape
arXiv:2609.16777v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against extit{persuasion attacks}---attem
arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and
arXiv:2604.05012v2 Announce Type: replace-cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value
arXiv:2601.18493v2 Announce Type: replace Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-cen
arXiv:2511.02831v2 Announce Type: replace Abstract: The data for remote sensing is constantly acquired, and new data comes from a growing number and diversity of satellites, while the vast majority of
Giving an assistant extra tools seems harmless. Surprisingly, this paper shows it can make the assistant stop answering questions it knows. Across six models, the answer rate on questions that need no
GitHub: https://github.com/pfekin/LARA I've been working on LARA (Lightweight Additive Residual Adaptation), a research project on making post-training modular for frozen language models. I've also de
arXiv:2609.16161v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive capabilities across a range of natural language processing tasks, and LLM inference has emerged as a
arXiv:2603.11515v2 Announce Type: replace Abstract: Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design s
arXiv:2609.17152v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are central to most modern vision models, yet obtaining input attributions that are fine-grained, faithful, and stable rema
arXiv:2609.16665v1 Announce Type: cross Abstract: Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additiona
arXiv:2602.03344v2 Announce Type: replace-cross Abstract: Robustness is widely viewed as a key challenge for real-world applications. However, because current research focuses only on difficult tasks,
arXiv:2609.16800v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remai
The essay below from Aaronson is just unmoored from reality, sorry. It is just not true, if you try to approach the question in a data-oriented fashion, rather than via vibes and speculative fiction a
arXiv:2609.16076v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at programming tasks but frequently fail at deterministic, fine-grained reasoning in natural language, relying heav
arXiv:2607.09709v2 Announce Type: replace Abstract: Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact. We study the
arXiv:2603.21676v2 Announce Type: replace-cross Abstract: Standard Transformers have a fixed computational depth, limiting their ability to generalize to tasks that require variable-depth reasoning. T
arXiv:2609.16098v1 Announce Type: cross Abstract: Large Language Model (LLM) agents have demonstrated impressive capabilities across a variety of domains, particularly when integrated with external to
arXiv:2609.15007v1 Announce Type: new Abstract: Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consisten
Today, we are announcing the availability of Agent Substrate on Google Kubernetes Engine (GKE). Agent Substrate is an open-source, secure-by-default agent execution runtime engineered to run millions
arXiv:2609.14824v1 Announce Type: new Abstract: The emergence of large language models (LLMs) and large multimodal models (LMMs) has enabled a new class of agentic systems capable of integrating natur
arXiv:2609.14262v1 Announce Type: new Abstract: Joint source localization and geoacoustic inversion requires optimizing an objective built from an expensive normal mode propagation model. Bayesian opt
arXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers
arXiv:2609.14754v1 Announce Type: cross Abstract: Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an in
arXiv:2609.14726v1 Announce Type: cross Abstract: Large language models are increasingly used to scale codebook-based annotation in scientific research, but existing workflows provide limited support
arXiv:2511.13725v5 Announce Type: replace-cross Abstract: Malicious AI causing harm to humans is not just a Hollywood fantasy. Indeed, as highly capable models such as Claude Mythos emerge and agent s