Knowledge catalogue
arXiv:2605.22208v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios by flexibly selecting
arXiv:2605.22020v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is funda
arXiv:2605.22413v1 Announce Type: new Abstract: Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multi
arXiv:2605.21901v1 Announce Type: new Abstract: In communicationless environments, multi-robot systems must operate without the constant information exchange that many coordination strategies typicall
arXiv:2605.22064v1 Announce Type: new Abstract: Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B,
Pixal3D is a Tencent image-to-3D model that generates high-fidelity 3D assets from a single image by explicitly lifting pixel features into 3D through back-projection to establish direct pixel-to-3D c
arXiv:2510.00948v2 Announce Type: replace Abstract: Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent c
arXiv:2605.21980v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understand
Introducing Qwen3.7-Max from @Alibaba_Qwen, Qwen’s flagship model for the agent era with 1M context and leading performance across agentic coding, reasoning, and long-horizon autonomy. AI natives can
arXiv:2605.22504v1 Announce Type: cross Abstract: Collaborative driving aims to improve safety and efficiency by enabling connected vehicles to coordinate under partial observability. Recent approache
arXiv:2605.21573v1 Announce Type: new Abstract: We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with
arXiv:2605.12321v2 Announce Type: replace Abstract: Large language models (LLMs) show strong potential for Intelligent Transportation Systems (ITS), particularly in tasks requiring situational reasoni
arXiv:2605.21804v1 Announce Type: cross Abstract: Field-scale crop maps support supply-chain forecasting and policy, yet statewide crop identification still often depends on retrospective surveys or r
arXiv:2605.21954v1 Announce Type: new Abstract: Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untrimmed video, is a key test of whether multimodal la
arXiv:2605.22121v1 Announce Type: new Abstract: Magnetic resonance imaging (MRI) is highly susceptible to patient motion due to its relatively long acquisition times and the fact that data are acquire
NuExtract3 is a unified 4B vision-language reasoning model for document understanding that combines structured information extraction with image-to-Markdown conversion, suitable for OCR and RAG prepro
arXiv:2605.21726v1 Announce Type: new Abstract: The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the
arXiv:2511.08093v2 Announce Type: replace-cross Abstract: Large speech recognition models like Whisper-small achieve high accuracy but are difficult to deploy on edge devices due to their high computa
arXiv:2605.21781v1 Announce Type: new Abstract: Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for
arXiv:2605.12334v2 Announce Type: replace Abstract: Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to ad
arXiv:2605.21788v1 Announce Type: new Abstract: Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VL
arXiv:2605.22511v1 Announce Type: cross Abstract: Post-training has become the dominant recipe for turning a language model into a competent search-augmented reasoning agent. A line of recent work pus
arXiv:2605.22668v1 Announce Type: new Abstract: Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resol
arXiv:2605.22098v1 Announce Type: new Abstract: The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Mot
arXiv:2605.22403v1 Announce Type: new Abstract: Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG
ID-LoRA (Identity-Driven In-Context LoRA) enables identity-preserving audio-video generation by simultaneously dictating the scene's visual content, environmental acoustics, and speaking style while p
arXiv:2605.22357v1 Announce Type: new Abstract: Accurate segmentation of hepatic and portal vessels in contrast-enhanced computed tomography angiography (CTA) remains challenging due to complex vascul
arXiv:2605.22718v1 Announce Type: new Abstract: Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisit
arXiv:2605.20495v1 Announce Type: new Abstract: Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality
arXiv:2605.21288v1 Announce Type: new Abstract: Tabular foundation models with different architectures converge in accuracy across a range of classification and regression tasks. This raises questions
arXiv:2602.04916v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have significantly advanced protein representation learning. However, their capacity to interpret and design anti
arXiv:2512.23292v3 Announce Type: replace-cross Abstract: The prevailing paradigm in AI for physical systems (scaling general-purpose foundation models toward universal multimodal reasoning) confronts
At Google I/O 2026, we announced updates to the integration between Google AI Studio and Google Cloud: New users can deploy up to two full-stack applications to the Google Cloud Starter Tier, no billi
arXiv:2605.21063v1 Announce Type: new Abstract: Typical LLM responses tend to follow a default style, even though users often have distinct preferences regarding tone, verbosity, and formality that th
arXiv:2605.21301v1 Announce Type: cross Abstract: In biomedical Subgroup Discovery, practitioners are interested in discovering interpretable and homogeneous subgroups within a group of patients. In t
arXiv:2605.20643v1 Announce Type: cross Abstract: Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the
Release b9255 of llama.cpp features a Hexagon HMX quantized matmul rework (#23368), including updates to debug logging, dequantization logic using HVX vectors, removal of non-pipelined quantization op
Release b9259 of llama.cpp fixes a nullptr crash in the speculative common module's get_devices_str function (PR #23386). The fix addresses an issue where ggml_backend_dev_by_name appends a nullptr se
Release b9260 of llama.cpp includes OpenCL backend refactoring that improves initialization, GPU identification, and performance by caching global memory size in device context. llama.cpp enables LLM
b9264 is a llama.cpp release that includes improvements to HunyuanVL model support, merging HunyuanOCR functionality and fixing vision precision issues. This build represents an intermediate developme
arXiv:2602.08819v2 Announce Type: replace-cross Abstract: Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to
arXiv:2509.07120v2 Announce Type: replace Abstract: Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models li
arXiv:2605.20341v1 Announce Type: new Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is co
arXiv:2605.20385v1 Announce Type: new Abstract: Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the
arXiv:2505.17354v3 Announce Type: replace Abstract: In many real-world settings--e.g., single-cell RNA sequencing, mobility sensing, and environmental monitoring--data are observed only as temporally
arXiv:2605.20811v1 Announce Type: new Abstract: Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations com
arXiv:2605.21139v1 Announce Type: new Abstract: Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement
arXiv:2605.20448v1 Announce Type: new Abstract: Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-c
arXiv:2605.20743v1 Announce Type: cross Abstract: Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expresse
arXiv:2605.20620v1 Announce Type: new Abstract: Shapley-based data valuation provides a principled way to quantify the contribution of training data, but its high computational cost makes it impractic
arXiv:2605.21282v1 Announce Type: new Abstract: Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and hav
arXiv:2603.16513v3 Announce Type: replace Abstract: Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation
arXiv:2602.16813v3 Announce Type: replace Abstract: Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive
arXiv:2510.14737v3 Announce Type: replace Abstract: Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the
arXiv:2605.20892v1 Announce Type: new Abstract: Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-qu
arXiv:2605.20316v1 Announce Type: new Abstract: Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified visi
arXiv:2602.10408v2 Announce Type: replace-cross Abstract: Normalization layers are standard in transformers, but it is not clear whether their sample-dependent computations are necessary throughout bo
arXiv:2605.20752v1 Announce Type: new Abstract: Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-lan
arXiv:2605.20476v1 Announce Type: new Abstract: Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are cont
arXiv:2509.10308v2 Announce Type: replace Abstract: In the aftermath of disasters, many institutions worldwide face challenges in monitoring changes in disaster risk, limiting assessment of progress t