Knowledge catalogue
arXiv:2607.23917v1 Announce Type: new Abstract: We introduce a novel learning problem: decoding gaze into natural language descriptions of human goals across diverse visual tasks. Unlike prior work, w
arXiv:2607.22757v1 Announce Type: cross Abstract: We introduce Graded Large Language Models (GLLMs), an algebraic framework that equips the representation space of a transformer with a grading and pro
arXiv:2603.14807v3 Announce Type: replace Abstract: LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods prima
arXiv:2607.22902v1 Announce Type: new Abstract: Creating sprint backlogs requires considerable effort, as items such as epics, user stories, and tasks can be missed or inconsistently specified. We pro
If I only went off X posts, I'd think Ramp was an AI lab We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation. It now spans from hybrid attention m
arXiv:2607.23808v1 Announce Type: cross Abstract: In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus
arXiv:2607.24260v1 Announce Type: new Abstract: Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structured priors, such as ranked evidence, graph topology
Kimi K3 has everyone’s attention. On July 30, hear @Kimi_Moonshot's Feihu Tang explain the architecture and decisions behind it. He joins Jue Wang and Zain Hasan from Together AI for a deep dive into
arXiv:2607.15928v2 Announce Type: replace Abstract: Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transf
arXiv:2607.23704v1 Announce Type: cross Abstract: The deployment of embodied agents in self-driving laboratories could accelerate scientific discovery, yet their reliability is constrained by the irre
arXiv:2607.23488v1 Announce Type: cross Abstract: Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, a
arXiv:2607.24064v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality imag
arXiv:2607.24224v1 Announce Type: new Abstract: Multi-modality data from different sensors provides rich complementary information for 3D perception, becoming an essential component in reliable autono
arXiv:2607.23576v1 Announce Type: new Abstract: Conventional frame-based cameras face significant challenges in detecting objects under high-speed motion blur or in low-light environments. Neuromorphi
arXiv:2607.24098v1 Announce Type: new Abstract: Referring video object segmentation (RVOS) requires segmenting a target specified by natural language throughout a video. Recent agentic approaches comb
The Kimi K3 architecture figure for yesterday's big open-weight model release, along with some observations and thoughts. 1. Yes, it looks relatively complicated, but it's essentially a scaled-up prod
arXiv:2607.24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur
arXiv:2607.23181v1 Announce Type: new Abstract: Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen sc
arXiv:2607.24082v1 Announce Type: new Abstract: Recent advances in AI have substantially expanded its cognitive and reasoning capabilities. From the perspective of semantic complexity, the development
arXiv:2607.22727v1 Announce Type: new Abstract: Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can
arXiv:1502.05678v3 Announce Type: replace Abstract: People preserve memories of events such as birthdays, weddings, or vacations by capturing photos, often depicting groups of people. Invariably, some
arXiv:2607.23472v1 Announce Type: new Abstract: Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficu
arXiv:2607.22632v1 Announce Type: new Abstract: The rapid rise of vlogs as a personalized storytelling medium has created a demand for automated systems to evaluate and refine vlog editing plans. Howe
arXiv:2607.22781v1 Announce Type: cross Abstract: High task performance does not show whether a model retains prediction-relevant structural information in its internal representation. Temporal graph
arXiv:2607.22035v1 Announce Type: new Abstract: Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infr
arXiv:2607.21617v1 Announce Type: cross Abstract: Vision Language Models (VLMs) are increasingly used in place of traditional OCR pipelines for document understanding. In this paper, we show they do n
arXiv:2607.21881v1 Announce Type: new Abstract: Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accountin
arXiv:2607.22268v1 Announce Type: cross Abstract: Remaining useful life (RUL) prediction and failure-mode classification are central tasks in predictive maintenance. Many data-driven pipelines use fix
arXiv:2602.05988v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their p
arXiv:2607.21953v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) communication is expected to support a wide range of low-altitude applications in 6G mobile networks. However, traditional
arXiv:2607.22100v1 Announce Type: new Abstract: Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into t
arXiv:2607.21653v1 Announce Type: cross Abstract: Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstrea
New research from NVIDIA. They just dropped a PyTorch-native training framework for agentic RL. (bookmark it) Paper summary: Molt is a PyTorch-native agentic RL framework with an unusual design target
Very cool paper from Microsoft. The idea is to train agents on replayed teacher trajectories instead of live environment rollouts. On-policy distillation for agentic tasks is expensive because every u
Recent discussions about open-sourcing make me feel that I should go back and revisit these important open-source works in representation learning that pushed the field forward and eventually made vis
arXiv:2607.21424v1 Announce Type: new Abstract: Recent advancements in automated audio captioning (AAC) have shifted from monolithic sentence generation toward structured formats that explicitly disen
arXiv:2607.20550v1 Announce Type: cross Abstract: The traditional 'one drug, one target' paradigm of structure-based drug design (SBDD) frequently proves inadequate for treating multifactorial disease
arXiv:2607.21027v1 Announce Type: new Abstract: Current identity customized video generation methodologies are predominantly limited to single-identity scenarios, as the lack of explicit identity sepa
arXiv:2607.21522v1 Announce Type: cross Abstract: Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graph
arXiv:2607.20462v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into clinical workflows, stressing the need for reliable traceability of model-generated output
arXiv:2607.21570v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise for medical education, but most existing systems focus on localized interactions such as question answering or
arXiv:2607.21404v1 Announce Type: new Abstract: While memory systems are essential for agent architectures, pervasive architectural fragmentation restricts systematic research. Existing implementation
arXiv:2607.21290v1 Announce Type: cross Abstract: Multi-task learning (MTL) is a promising approach for prediction tasks derived from video game state data, as modern game telemetry provides multiple
arXiv:2607.21061v1 Announce Type: new Abstract: Affective Image Content Analysis (AICA) aims to recognize and understand emotions elicited by visual content, representing an indispensable step toward
arXiv:2607.21557v1 Announce Type: new Abstract: Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to e
arXiv:2504.16318v3 Announce Type: replace Abstract: Cosine similarity is a standard comparison rule for learned representations in information retrieval, natural language processing, computer vision,
arXiv:2607.20912v1 Announce Type: new Abstract: Learning-based manipulation policies usually predict robot actions from sensory observations and leave their execution to a separate low-level controlle
arXiv:2607.21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens. Therefore, a safety guard that watches that answer has to keep up w
arXiv:2607.20057v1 Announce Type: cross Abstract: Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein langua
arXiv:2607.19827v1 Announce Type: new Abstract: Ensuring safety in Physical AI systems operating in real-world environments is a critical challenge, particularly in hospital wards where vulnerable pat
arXiv:2607.19046v1 Announce Type: new Abstract: On-policy Distillation (OPD) supervises a student model on trajectories sampled from its own policy by minimizing the divergence between the output dist
arXiv:2506.10890v2 Announce Type: replace Abstract: Graphic design plays a crucial role in both commercial and personal contexts, yet creating high-quality, editable, and aesthetically pleasing graphi
A Chinese article compiled 52 remarks from Liang Wenfeng’s four-hour investor meeting. I’ve summarised the most important ones below. DeepSeek has one central objective: AGI. This is not the time to m
arXiv:2607.19476v1 Announce Type: new Abstract: Detectors for AI-generated video are evaluated offline. A clip is decoded to pixels and scored once, increasingly by a large vision-language model. Dete
arXiv:2607.20087v1 Announce Type: new Abstract: Aims: Cardiovascular magnetic resonance (CMR) imaging enables non-invasive assessment of myocardial structure, function, and pathology, but requires sub
arXiv:2607.18958v1 Announce Type: new Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulne
arXiv:2607.19880v1 Announce Type: new Abstract: Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply differe
arXiv:2607.20092v1 Announce Type: cross Abstract: Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is rele
arXiv:2509.15868v2 Announce Type: replace Abstract: Large-scale land cover maps generated using deep learning play a critical role across a wide range of Earth science applications. Open in-situ datas
arXiv:2607.19811v1 Announce Type: new Abstract: The Segment Anything Model 2 (SAM2) has advanced temporal promptable segmentation, yet its deployment remains hindered by heavy memory cross-attention o