Knowledge catalogue
arXiv:2608.01113v1 Announce Type: new Abstract: Text-driven instruction-based video editing in complex scenes remains challenging: purely textual prompts often fail to capture precise spatial relation
arXiv:2608.00119v1 Announce Type: new Abstract: Rapid estimation of impacted structures - critical for conflict-zone humanitarian response - is frequently hindered by post-strike satellite data embarg
arXiv:2608.00371v1 Announce Type: new Abstract: We introduce a new problem domain for human action recognition: the fine-grained analysis of children's gait behaviors from standard RGB video. We speci
arXiv:2608.01848v1 Announce Type: new Abstract: Recent visual-text compression (VTC) methods, typified by DeepSeek-OCR, report impressive high token compression ratios for long-context modeling tasks
arXiv:2608.00146v1 Announce Type: new Abstract: We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rathe
arXiv:2608.01560v1 Announce Type: new Abstract: Scaling the corpus is the default remedy when a contrastive representation lacks an attribute. We report a case where it does nothing, and identify what
arXiv:2608.01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-
arXiv:2603.00919v3 Announce Type: replace Abstract: Large language models (LLMs) have shown great promise for autonomous driving. However, discretizing numbers into tokens limits precise numerical rea
arXiv:2603.12147v2 Announce Type: replace Abstract: Egocentric video provides a natural modality for studying human behavior, but conventional visual understanding captures mainly observable scenes, o
arXiv:2506.03270v3 Announce Type: replace Abstract: While recent advances in vision-language models have accelerated language-guided robot planning, their black-box nature lacks the safety guarantees
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:2608.01737v1 Announce Type: new Abstract: As digital drawings are increasingly shared online, reliable authorship verification has become important for protecting artists and resolving disputes.
arXiv:2608.02257v1 Announce Type: new Abstract: Mobile manipulation is a key capability for embodied intelligence, enabling robots to accomplish complex multi-stage tasks in open-world environments. H
Live and ready to build. Thanks for having us! @OpenRouter. Open weights dropping soon.⚡️ Qwen3.8 Max by @Alibaba_Qwen is live on OpenRouter. The new flagship has 2.4T parameters (95B active) and is b
arXiv:2608.00272v1 Announce Type: new Abstract: This paper proposes a localization framework that uses spatiotemporal fields governed by partial differential equations (PDEs) as localization signature
arXiv:2608.01742v1 Announce Type: cross Abstract: Long-term memory is critical for LLM agents operating over long-horizon interactions. However, several persistent limitations of existing memory syste
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:2608.00975v1 Announce Type: new Abstract: Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) app
arXiv:2608.02449v1 Announce Type: new Abstract: Deploying vision-language models (VLMs) for safety-critical spatial reasoning on resource-constrained autonomous driving platforms requires both compact
arXiv:2608.01807v1 Announce Type: new Abstract: Existing RGBT trackers typically employ fusion functions with fixed parameters across different targets and scenarios. Although dynamic-architecture met
arXiv:2608.00066v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact heart-rate estimation from facial videos, but its weak physiological signal is easily corrupted b
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:2510.22868v2 Announce Type: replace Abstract: Wind turbine blades operate in harsh environments, making timely damage detection essential for preventing failures and optimizing maintenance. Dron
arXiv:2608.01954v1 Announce Type: new Abstract: Fixed-layout indoor furniture styling requires selecting assets that form a coherent room without changing the prescribed furniture categories, position
arXiv:2608.01975v1 Announce Type: cross Abstract: Large language model (LLM) inference has evolved from an offline workload into a continuously operated software service, yet root-cause analysis remai
arXiv:2608.00561v1 Announce Type: cross Abstract: Vision-language models (VLMs) process image patches and text tokens in a shared residual stream, but the local geometry through which the two modaliti
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
arXiv:2510.03519v2 Announce Type: replace Abstract: Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time ser
arXiv:2608.01409v1 Announce Type: new Abstract: Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted, or unaddressed: they should also produce evidence
arXiv:2607.28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and
arXiv:2607.29112v1 Announce Type: cross Abstract: Audio-visual speech recognition (AVSR) relies on effective fusion of audio and visual modalities, yet existing approaches treat cross-modal interactio
arXiv:2607.18529v2 Announce Type: replace-cross Abstract: Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their pedagogical quality. Exist
arXiv:2607.29025v1 Announce Type: new Abstract: While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency
arXiv:2602.08913v3 Announce Type: replace Abstract: In underdetermined regression and classification problems, multiple feature subsets often yield equivalent predictive performance. In applied settin
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:2607.28674v1 Announce Type: new Abstract: Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpr
LWiAI Podcast #253 (July 29 2026) covers a roundup of recent AI developments: Anthropic introduced Claude Opus 5 with Fable‑like capabilities; Google released Gemini 3.6/3.5 “Flash” variants and a cyb
📢Meet Qwen3.8-Max — our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉 Qwen3.8-Max, a new bar for
arXiv:2512.08022v2 Announce Type: replace-cross Abstract: We propose a novel diffusion-based posterior sampling method within a plug-and-play framework. Our approach constructs a probability transport
arXiv:2607.28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning. These developments have accelerated the
arXiv:2607.29100v1 Announce Type: cross Abstract: Differentially private (DP) training of text-conditioned generative models suffers a utility cliff at strong privacy. We revisit this problem through
arXiv:2607.28680v1 Announce Type: new Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on
arXiv:2607.29482v1 Announce Type: new Abstract: By relying on independent couplings from uninformative Gaussian priors, standard diffusion and flow matching models are forced to learn complex, high-co
arXiv:2607.29090v1 Announce Type: new Abstract: Postoperative adverse events, including mortality and morbidity, remain a major global burden, many of which are preventable through early identificatio
TensorSharp supports DSpark on Deepseek v4 Flash 0731 now. Here is the benchmark result on 4x Nvidia A40 GPUs, cuda 12.8 with/without DSpark: Model: DeepSeek-V4-Flash-0731-UD-Q8_K_XL from https://hugg
We're starting to leave the territory where you'd test an LLM by e.g. 'create an svg of pelican on a bicycle'. As one idea to generalize it, I was interested what Opus 5 would do if I gave it the firs
arXiv:2512.02653v2 Announce Type: replace Abstract: Multi-view learning integrates diverse representations of the same instances and can improve performance when interactions across views are effectiv
arXiv:2511.22078v2 Announce Type: replace Abstract: Many real-world scenarios involving streaming information can be represented as temporal graphs, where data flows through dynamic changes in edges o
arXiv:2607.28618v1 Announce Type: new Abstract: Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems pr
arXiv:2607.27845v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled AI systems to assist scientific research and peer review. However, an essential capability
arXiv:2607.11623v3 Announce Type: replace Abstract: Real-world paired image dehazing remains challenging because haze degradation is spatially non-uniform, illumination-dependent, and physically ambig
arXiv:2512.00807v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation. Current fairness interve
arXiv:2607.27418v1 Announce Type: new Abstract: Long-term ship trajectory prediction is a fundamental capability for maritime safety and autonomous navigation. While recent Transformer-based architect
arXiv:2607.28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Se
arXiv:2510.05554v2 Announce Type: replace Abstract: As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity
arXiv:2607.27761v1 Announce Type: cross Abstract: In recent years, multi-view clustering has attracted widespread research interest. However, due to limitations in data collection devices, data across
arXiv:2607.27763v1 Announce Type: new Abstract: We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with tw
arXiv:2607.27614v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led sign language translation (SLT), the task of converting sign-language videos into spoken-langua
arXiv:2504.21174v2 Announce Type: replace Abstract: Deep learning drives a new wave in computing systems and triggers the automation of increasingly complex problems. In particular, Large Language Mod
arXiv:2607.28225v1 Announce Type: new Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulation, h