Knowledge catalogue
arXiv:2608.20210v1 Announce Type: cross Abstract: Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one u
arXiv:2608.20161v1 Announce Type: new Abstract: Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a
arXiv:2608.20052v1 Announce Type: new Abstract: Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches
Bloomberg: DeepSeek unveils an experimental multimodal version of its V4 Flash model, saying it nears the performance of Anthropic's Opus 4.8 on multimodal agentic tests — DeepSeek unveiled an experim
arXiv:2608.20258v1 Announce Type: new Abstract: Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decisio
arXiv:2608.19871v1 Announce Type: new Abstract: Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned fro
arXiv:2608.20141v1 Announce Type: new Abstract: All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model. However, existing methods often overlook image semantic
arXiv:2608.20308v1 Announce Type: new Abstract: Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object
arXiv:2608.19497v1 Announce Type: new Abstract: We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. U
arXiv:2608.19579v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes applications, yet their tendency to generate toxic, harmful, or policy-violating c
arXiv:2608.19880v1 Announce Type: new Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left be
arXiv:2608.20149v1 Announce Type: new Abstract: This article explores the performance of analytical and neural-based hillshading methods in a dense urban environment using high-resolution digital elev
arXiv:2608.19888v1 Announce Type: cross Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one,
arXiv:2608.19808v1 Announce Type: new Abstract: Cyclic peptides are emerging as promising molecular scaffolds in drug discovery due to their high binding affinity and structural stability. However, ex
arXiv:2608.19766v1 Announce Type: new Abstract: Self-supervised pretraining on remote sensing imagery typically treats all samples as equally informative, despite large variability in geographic and v
arXiv:2608.19490v1 Announce Type: cross Abstract: State-of-the-art vision-language-action (VLA) models such as pi_{0.5} exhibit strong semantic understanding, instruction following and task behavior.
arXiv:2608.19743v1 Announce Type: new Abstract: We describe our entry to the PhysAI Dynamic 4D Reconstruction Challenge, which placed third of 27 teams at 0.58356 APD on the final leaderboard, without
arXiv:2508.12682v2 Announce Type: replace Abstract: The global shift towards renewable energy presents unprecedented challenges for the electricity industry, making regulatory reasoning and compliance
Grok 4.6 just took #1 on CursorBench. Not only the highest score. It did it at a fraction of the cost of the models sitting right behind it. That combination is the real signal. Top-tier results are o
Impressive research from Google on building better environments for agents. Training environments for agents are hand-built and go stale. The agent improves, the environment does not, and it's not abl
arXiv:2608.19881v1 Announce Type: cross Abstract: Radio frequency (RF) fingerprinting authenticates wireless devices from hardware-induced I/Q impairments, typically with deep learning feature extract
arXiv:2608.19785v1 Announce Type: cross Abstract: Discovering dynamical systems from trajectory data is a central problem in applied mathematics and engineering. Whilst recent advances in machine lear
arXiv:2608.20256v1 Announce Type: new Abstract: Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which
arXiv:2608.19863v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on e
Hello gang, I made an implementation of DSpark PC Tree (Parent conditioned drafting tree). This is an implementation of this research paper: https://arxiv.org/abs/2608.02123 Unaffiliated, just found i
arXiv:2608.19800v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead. However
arXiv:2608.20011v1 Announce Type: new Abstract: Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow
arXiv:2608.19788v1 Announce Type: cross Abstract: Trustworthy multimodal fusion in clinical settings requires handling incomplete and heterogeneous modality subsets across institutions, where privacy
arXiv:2608.19914v1 Announce Type: new Abstract: Network topology inference from graph signals is central to graph signal processing with applications in neuroscience, sensor, and social networks. In p
Multimodal API support 🔌 🔹 Set model='deepseek-v4-flash-vision-exp' 🔹 Images are tokenized for billing: up to 384 tokens each, at V4-Flash pricing 🔹 Supports Chat Completions, Messages & Responses 🔹 S
NVIDIA’s Agentic Variation Operators (AVO) architecture delivers a frontier‑level general‑purpose agent by integrating persistent memory, supervision, and tool use within the system harness rather tha
arXiv:2608.20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing
arXiv:2608.19598v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, i
arXiv:2608.19906v1 Announce Type: new Abstract: Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP
arXiv:2608.20229v1 Announce Type: cross Abstract: Anatomically plausible segmentation remains challenging because of low contrast, ambiguous boundaries, and modality-specific artifacts. Interactive se
arXiv:2506.07459v4 Announce Type: replace Abstract: Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequenc
arXiv:2608.19306v1 Announce Type: cross Abstract: Given a set of input states, we consider the task of predicting the expectation value of a Pauli observable at the output of an unknown quantum evolut
arXiv:2604.05853v3 Announce Type: replace Abstract: Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and forma
arXiv:2608.19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard pr
arXiv:2608.19735v1 Announce Type: new Abstract: We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic cli
arXiv:2608.19890v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains. However, traditional TTA methods become ineffecti
arXiv:2608.19689v1 Announce Type: new Abstract: LLM-based social simulation is a promising complement to traditional methods such as surveys and behavioral experiments. A core question is how to evalu
arXiv:2503.04500v3 Announce Type: replace-cross Abstract: Video understanding has largely relied on deep spatiotemporal architectures, including 3D convolutional networks and optical flow (OF) based m
arXiv:2608.19693v1 Announce Type: new Abstract: Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented realit
arXiv:2606.18632v2 Announce Type: replace Abstract: Embodied Foundation Models (EFMs) integrate multimodal understanding, future-state reasoning, and executable robot actions. Yet their safety alignme
arXiv:2608.20208v1 Announce Type: new Abstract: Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction. Yet prevalent diffusio
arXiv:2608.19669v1 Announce Type: new Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visu
arXiv:2608.20005v1 Announce Type: new Abstract: Pretraining time series foundation models across heterogeneous datasets necessitates effective handling of varying sampling frequencies. Current methods
arXiv:2608.19719v1 Announce Type: cross Abstract: Reference-based diffusion stylization requires separating target geometry from transferable appearance. Existing tuning-based methods often rely on al
arXiv:2608.19885v1 Announce Type: cross Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one,
arXiv:2608.19907v1 Announce Type: new Abstract: This paper presents a Bayesian control framework that integrates spike-based dynamics with probabilistic inference for adaptive control. Bayesian infere
arXiv:2607.13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning
arXiv:2608.19799v1 Announce Type: new Abstract: Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program
arXiv:2608.19882v1 Announce Type: new Abstract: Deep learning models remain vulnerable to real-world input perturbations, especially when multiple corruptions co-occur in the same input (e.g., brightn
arXiv:2608.19899v1 Announce Type: cross Abstract: Machine learning (ML) is widely used for the development of ocean colour algorithms, but most studies focus on model parameter training and hyperparam
This is very nice work from NVIDIA. Like all high-performing approaches on ARC-AGI-3, it uses deep learning-guided on-the-fly synthesis of symbolic world models, i.e. navigating the world by generatin
arXiv:2608.20263v1 Announce Type: new Abstract: We propose UHDformer++, a general Transformer-based framework to solve numerous Ultra-High-Definition (UHD) image restoration tasks. UHDformer++ operate
Hey locallama! We recently open sourced a Qwen3-TTS 1.7B implementation that achieves 10 requests per second (RPS) and sub-50 ms p95 time-to-first-audio (TTFA) while maintaining real-time playback on
arXiv:2608.19583v1 Announce Type: cross Abstract: Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable eva
arXiv:2601.07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of v