Knowledge catalogue
arXiv:2607.03633v1 Announce Type: new Abstract: Identity recognition (e.g., person, animal re-identification) has traditionally relied heavily on static appearance cues. Yet motion--consistent, indivi
arXiv:2607.03801v1 Announce Type: cross Abstract: We define Tiny Language Models (TLMs) as models below roughly 3B parameters that fit on mainstream consumer devices. We study how to adapt them for an
arXiv:2505.09484v2 Announce Type: replace Abstract: Face Anti-Spoofing (FAS) is essential for the security of facial recognition systems in diverse scenarios such as payment processing and surveillanc
arXiv:2602.20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated ev
arXiv:2511.05730v2 Announce Type: replace Abstract: In this paper, a learning framework is introduced which incorporates principles of probabilistic inference, variational optimization, and geometry-p
arXiv:2607.04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.5-4B on a resource-constr
arXiv:2509.14026v2 Announce Type: replace-cross Abstract: Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highli
arXiv:2607.02921v1 Announce Type: cross Abstract: Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmark
arXiv:2607.05171v1 Announce Type: new Abstract: Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computa
Application and network security company Radware Ltd. today expanded its Agentic AI Protection product with compliance reporting, deeper visibility into artificial intelligence agent activity, and new
arXiv:2508.08983v2 Announce Type: replace-cross Abstract: Humans can learn a new manipulation task from one or two demonstrations and then perform it in a new room, with new objects, under new constra
arXiv:2607.02711v1 Announce Type: new Abstract: Recent 3D foundation models, such as DUSt3R, MASt3R, VGGT, pi^3, and Depth Anything 3, provide strong feed-forward depth and pose estimates on pinhole i
arXiv:2607.03502v1 Announce Type: cross Abstract: Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visi
arXiv:2601.14788v2 Announce Type: replace Abstract: Diffusion models have seen widespread adoption for text-driven human motion generation and related tasks due to their impressive generative capabili
arXiv:2606.12742v3 Announce Type: replace Abstract: Wearable healthcare devices are the fastest-growing Internet of Things (IoT) sector. Many automated healthcare services rely on two crucial biologic
arXiv:2507.16331v4 Announce Type: replace Abstract: Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant cha
arXiv:2607.03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine ou
arXiv:2607.02957v1 Announce Type: new Abstract: Single-image reflection removal (SIRR) aims to recover the clean transmission layer from a reflection-contaminated image. Although recent methods achiev
For years, enterprise AI has been synonymous with conversational AI — the customer service bots and digital assistants we interact with every day. But today, the market has shifted. We’ve officially m
DeepSeek Ltd., one of China’s most visible artificial intelligence companies, is pushing to design its own, in-house silicon aimed at inference workloads, according to a report by Reuters today. The r
arXiv:2607.02687v1 Announce Type: cross Abstract: Intrusion detection systems are often trained under static benchmark conditions, although deployed network environments are affected by traffic drift,
arXiv:2607.04438v1 Announce Type: cross Abstract: Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifa
arXiv:2607.03591v1 Announce Type: cross Abstract: Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured cras
arXiv:2607.03680v1 Announce Type: cross Abstract: Recent AI-generated text detection work often introduces a new benchmark together with a specialized detector tailored to it. We revisit this practice
arXiv:2607.04645v1 Announce Type: cross Abstract: Safety alignment in large language models is typically evaluated against direct, imperative harmful requests. We show that this alignment is highly co
arXiv:2607.03058v1 Announce Type: new Abstract: Post-refinement can improve colonoscopy segmentation after host inference, but many designs still rely on extra correction heads or multi-stage pipeline
arXiv:2607.04281v1 Announce Type: cross Abstract: Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but m
arXiv:2607.04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent work has increasingly favored reinf
arXiv:2510.17801v2 Announce Type: replace-cross Abstract: Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a central challenge. Recent embodied systems
arXiv:2607.04434v1 Announce Type: cross Abstract: Generalist robot manipulation policies have advanced rapidly, yet existing benchmarks remain limited in systematically evaluating their capabilities.
arXiv:2607.04610v1 Announce Type: new Abstract: Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, a
arXiv:2607.03694v1 Announce Type: new Abstract: Large-scale Capacitated Vehicle Routing Problems (CVRPs) are commonly solved by partitioning customers into smaller routing problems that can be optimiz
arXiv:2508.11657v2 Announce Type: replace-cross Abstract: Objective: Sparse Bayesian learning provides an effective framework to solve high-dimensional problems in brain signal decoding. However, conv
arXiv:2607.03075v1 Announce Type: cross Abstract: Safety-critical applications require classifiers that are both robust and reliable. Adversarial training is a widely adopted defense for improving rob
arXiv:2607.04729v1 Announce Type: cross Abstract: LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable
arXiv:2607.02689v1 Announce Type: cross Abstract: As wearable devices enable continuous first-person recording, AI assistants must reason across long time horizons to recall past experiences-a capabil
arXiv:2607.04306v1 Announce Type: cross Abstract: Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not exp
arXiv:2607.03069v1 Announce Type: new Abstract: As video generation paradigms evolve from localized manipulation to full-scene synthesis, AI-generated video detection becomes increasingly challenging,
arXiv:2607.04017v1 Announce Type: new Abstract: Human object interaction (HOI), gaze pattern, and their anticipation are intricately linked, providing valuable insights into cognitive processes, inten
Sakana AI (@SakanaAILabs) is now a model vendor on Merge Gateway, and Fugu Ultra is live through them. It's a multi-agent orchestration model that routes across frontier models behind one API. You get
arXiv:2607.05259v1 Announce Type: new Abstract: Sentiment analysis has been a primary domain under Natural Language Processing (NLP) from its inception as it plays a vital role in both real-world and
arXiv:2607.04540v1 Announce Type: cross Abstract: Geometry-conditioned 3D scene generation enables the creation of 3D environments from user-provided geometry, offering direct control over scene struc
arXiv:2607.02802v1 Announce Type: cross Abstract: As LLMs are increasingly deployed as autonomous adjudicators in semi-open textual game environments, robust rule adherence becomes critical when user
arXiv:2606.13033v2 Announce Type: replace Abstract: Multi-object tracking has a heavy-tailed difficulty distribution: most frames are easy for a lightweight base tracker, while a small fraction are in
arXiv:2510.09458v2 Announce Type: replace-cross Abstract: Interest in forestry automation is growing alongside rapid advances in deep learning. In particular, tree detection and taxonomic classificati
arXiv:2603.19873v2 Announce Type: replace Abstract: Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and d
arXiv:2607.03451v1 Announce Type: cross Abstract: While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question una
arXiv:2607.04764v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) in lifelong deployment requires continuous adaptation to new environments without catastrophic forgetting. In this pape
arXiv:2607.05187v1 Announce Type: new Abstract: As CMOS technology scales into the deep nanometer regime, digital circuit reliability is increasingly threatened by the combined stochastic effects of B
arXiv:2511.09072v2 Announce Type: replace-cross Abstract: Traditional Visual Odometry (VO) and Visual Inertial Odometry (VIO) methods rely on a 'pose-centric' paradigm, which computes absolute camera
arXiv:2607.03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding k
arXiv:2607.04234v1 Announce Type: cross Abstract: Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the
arXiv:2607.04694v1 Announce Type: new Abstract: As vision-language models (VLMs) are increasingly applied to medical AI, existing benchmarks mainly focus on evaluating their diagnosis ability over giv
Reuters: Sources: DeepSeek is in the early stages of developing its own AI chip designed for inference, in a bid to reduce its reliance on Nvidia and Huawei hardware — Chinese startup DeepSeek is deve
Sovereign AI belongs in all regions of the world. We’re working hard to make it accessible to everyone. Model weights are available on @huggingface. Run it anywhere from corporate hardware to your per
arXiv:2607.02814v1 Announce Type: cross Abstract: Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, appealing platform decisions, escalating s
arXiv:2607.05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negot
arXiv:2511.07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial rea
arXiv:2607.05365v1 Announce Type: cross Abstract: Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks d
arXiv:2603.23483v2 Announce Type: replace-cross Abstract: Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through