Knowledge catalogue
arXiv:2608.02433v1 Announce Type: new Abstract: Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using
arXiv:2608.02064v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) account for a large fraction of Transformer parameters, yet their hidden width is usually constant across depth. We ask w
arXiv:2608.02124v1 Announce Type: cross Abstract: Vision-language models (VLMs) remain unreliable when predictions require fine-grained visual evidence. We identify a previously overlooked cause: spec
arXiv:2608.02087v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM
arXiv:2608.00237v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs
arXiv:2608.00079v1 Announce Type: new Abstract: Long-form and real-time talking-head generation remains challenging due to a latency-quality trade-off: inefficient multi-step diffusion prohibits strea
arXiv:2608.02134v1 Announce Type: new Abstract: Modern vision language models (VLMs) turn high-resolution images into long sequences of visual tokens. Every token traverses the language decoder and pe
arXiv:2608.00847v1 Announce Type: new Abstract: Most current visual trackers adopt a matching-based architecture trained exclusively on tracking datasets, whose performance gains depend heavily on the
arXiv:2409.15600v3 Announce Type: replace Abstract: A representation of a molecule or material should be invariant to the symmetries of physics, unique, continuous, efficient and general. These proper
arXiv:2608.01793v1 Announce Type: new Abstract: Unified anomaly detection requires modeling highly heterogeneous normal data without access to anomalous samples. While foundation models like DINOv2 pr
arXiv:2608.01314v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthe
arXiv:2608.00943v1 Announce Type: cross Abstract: Automated sleep staging assigns discrete stage labels to successive time epochs throughout an overnight recording; conventionally each window spans at
arXiv:2608.02508v1 Announce Type: cross Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the inte
arXiv:2608.00463v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) turns captured or generated imagery into photorealistic 3D world simulations that users can freely explore, yet these world
arXiv:2608.02358v1 Announce Type: new Abstract: To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone,
arXiv:2608.02139v1 Announce Type: new Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transformin
arXiv:2608.01659v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set o
arXiv:2608.02499v1 Announce Type: cross Abstract: Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task,
arXiv:2608.01724v1 Announce Type: new Abstract: Group conversations are fundamental to human collaboration, yet standard large language models (LLMs) still struggle with the complexities of multi-part
arXiv:2608.02401v1 Announce Type: new Abstract: Hyperspectral image super-resolution aims to reconstruct high-resolution imagery while preserving dense spectral information. Recently, Mamba-based mode
arXiv:2608.00094v1 Announce Type: new Abstract: Pretrained video diffusion models can act as renderers when the desired scene state is already specified by an animated mesh, a camera trajectory, and a
arXiv:2608.01851v1 Announce Type: new Abstract: Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that w
arXiv:2608.01880v1 Announce Type: new Abstract: World Action Models generate fixed-horizon action chunks through iterative denoising, creating substantial inference latency that can cause pauses, stal
arXiv:2607.28968v1 Announce Type: cross Abstract: Renault, Bergeaud, and Bosquet (hereafter RBB) argue that dating LLM adoption as the first month in which an author's abstract is flagged induces a st
arXiv:2604.02330v2 Announce Type: replace-cross Abstract: Recent advances in video diffusion have enabled the development of 'world models' capable of simulating interactive environments. However, the
arXiv:2602.10429v2 Announce Type: replace-cross Abstract: AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent arc
arXiv:2607.28818v1 Announce Type: new Abstract: As AI companions increasingly mediate repeated social interaction, users may rely on a stable role and shared history, yet locally acceptable replies do
arXiv:2607.29402v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems synergize retrieval mechanisms with generative language models to enhance the accuracy and relevance of r
arXiv:2607.28691v1 Announce Type: cross Abstract: Personalized AI agents are often configurable without giving users control over the artifacts that determine their future behavior. We present OurArk,
arXiv:2607.18622v2 Announce Type: replace-cross Abstract: Textual Collaborative Prompt Optimization (TCPO) extends TextGrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple c
arXiv:2607.29577v1 Announce Type: new Abstract: Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reas
arXiv:2607.29058v1 Announce Type: new Abstract: Professional-document review is a constraint-checking problem in which decisions depend on relations among text, geometry, pages, and document revisions
arXiv:2607.29484v1 Announce Type: new Abstract: Interventional data is widely regarded as the gold standard for teaching models causal reasoning. We test this assumption in a fully controlled syntheti
arXiv:2607.29665v1 Announce Type: new Abstract: PDE discovery from sparse observations requires reconstructing a continuous field and selecting the correct differential terms. Our analysis of optimiza
arXiv:2603.29888v2 Announce Type: replace-cross Abstract: In collaboration with Alibaba, we study how a generative AI assistant affects service performance in e-commerce after-sales operations. In a l
arXiv:2607.29600v1 Announce Type: new Abstract: Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has eme
arXiv:2607.28652v1 Announce Type: cross Abstract: Early-life monitoring in laying hens remains constrained by fragmented single-modality sensing and the absence of formal system-level state representa
arXiv:2607.29509v1 Announce Type: new Abstract: Effective multi-organ segmentation in surgical data requires learning the intricate anatomical features and alleviating the challenge of class imbalance
arXiv:2607.28956v1 Announce Type: new Abstract: Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success crite
arXiv:2607.28751v1 Announce Type: new Abstract: Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings thro
arXiv:2607.29124v1 Announce Type: new Abstract: Scientific figures often encode the visual evidence behind scientific findings, yet figure plagiarism remains underexplored as a benchmarked multimodal
arXiv:2607.29503v1 Announce Type: new Abstract: While neural networks are typically evaluated by their training and test performance, these metrics do not reveal how robust a learned representation is
Hey everyone, I'm reaching out to see if anyone else has run into a similar issue or if there's an alternative way to reach their team. I subscribed to the Ollama Max plan on June 17th. Everything was
# Running DeepSeek-V4-Flash-0731 (155 GB MoE) on a DGX Spark with vLLM-Moet 2-bit quantization I used Deepseek-v4-Flash-0731 cloud API settig up vllm-moet to run deepseek-v4-flash with MTP locally on
For anyone interested, here are the llama-bench results on 3 bit K_XL quantization. I think this could be pushed further but no luck so far. CURRENT RESULTS: full moe offloading Prefill suffers 116 --
arXiv:2505.10300v2 Announce Type: replace-cross Abstract: Responsible AI (RAI) efforts increasingly emphasize the importance of addressing potential harms early in the AI development lifecycle through
arXiv:2607.27705v1 Announce Type: cross Abstract: Large language models can contribute useful ideas to mathematical research, yet long-horizon proof attempts remain difficult to coordinate, evaluate,
arXiv:2607.27512v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among int
arXiv:2607.28308v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected exper
arXiv:2607.26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% def
arXiv:2607.28513v1 Announce Type: new Abstract: Creativity is often framed as the production of novelty, yet many cultural works emerge through transformation of earlier artifacts and not through isol
I'm an avid user of Deepseek v4 Flash via antirez's DS4 DwarfStar inference engine, and so when the new checkpoint dropped, the first thing I did was rent a cloud box and spin up a quantization for us
arXiv:2607.27914v1 Announce Type: new Abstract: Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators. Model
arXiv:2607.27280v1 Announce Type: cross Abstract: Robust Optimization Over Time (ROOT) is a recent branch of evolutionary dynamic optimization that seeks solutions capable of remaining effective acros
arXiv:2607.27844v1 Announce Type: cross Abstract: Physical computing leverages complex dynamical systems for energy-efficient data processing. In this work, we present a neuromorphic architecture base
arXiv:2607.27475v1 Announce Type: cross Abstract: In modern recommendation systems, retrieval serves as a primary stage responsible for filtering billions of candidate items down to thousands prior to
arXiv:2607.27782v1 Announce Type: new Abstract: Flow-matching Vision-Language-Action (VLA) policies have shown strong potential for robotic manipulation but often suffer from compounding errors caused
arXiv:2607.26314v1 Announce Type: cross Abstract: Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisti
arXiv:2607.27383v1 Announce Type: new Abstract: We establish the first convergence guarantees for the plain vector-form Adam optimizer under heavy-tailed stochastic noise. While several Adam variants
arXiv:2607.28259v1 Announce Type: new Abstract: We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friend