Knowledge catalogue
arXiv:2510.01186v2 Announce Type: replace Abstract: While existing video editing methods excel with single subjects, they struggle in dense, multi-subject scenes, frequently suffering from attention d
Banger paper from NVIDIA. Agentic reasoning needs models that are not just capable, but efficient at long-context inference. The agent model layer is moving toward open, long-context, high-throughput
arXiv:2604.12221v1 Announce Type: new Abstract: Gait recognition, as a reliable biometric technology, has seen rapid development in recent years while it faces significant challenges caused by diverse
arXiv:2604.12138v1 Announce Type: new Abstract: RAG systems have transformed how LLMs access external knowledge, but we find that current implementations exhibit a bias toward factual, objective conte
arXiv:2604.12196v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate multiple candidate responses for a given prompt, yet selecting the most reliable one remains challengin
arXiv:2604.12119v1 Announce Type: new Abstract: Large vision-language models (VLMs) often rely on familiar semantic priors, but existing evaluations do not cleanly separate perception failures from ru
arXiv:2604.12325v1 Announce Type: cross Abstract: We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past expe
arXiv:2604.12966v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-gr
arXiv:2508.18187v2 Announce Type: replace-cross Abstract: Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become w
arXiv:2604.12341v1 Announce Type: new Abstract: As generative image editing advances, image manipulation localization (IML) must handle both traditional manipulations with conspicuous forensic artifac
arXiv:2604.12632v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity th
arXiv:2602.00181v3 Announce Type: replace-cross Abstract: Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat t
arXiv:2604.12262v1 Announce Type: cross Abstract: Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, singl
arXiv:2507.21990v4 Announce Type: replace-cross Abstract: Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoni
arXiv:2604.12767v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing
arXiv:2501.06268v3 Announce Type: replace Abstract: We propose a graph-based clustering method based on Cluster Catch Digraphs (CCDs) that extends their applicability to moderate-dimensional data sett
arXiv:2604.12913v1 Announce Type: cross Abstract: Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large L
arXiv:2601.11047v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities but often grapple with reliability challenges like hallucinations.
arXiv:2604.12777v1 Announce Type: cross Abstract: The human brain constructs emotional percepts not by processing facial expressions in isolation, but through a dynamic, hierarchical integration of se
arXiv:2604.12359v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain atta
arXiv:2604.11991v1 Announce Type: new Abstract: Many problems in robotics require reasoning over a mix of continuous dynamics and discrete events, such as making and breaking contact in manipulation a
arXiv:2604.12308v1 Announce Type: new Abstract: Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires
AI and cloud technology are reshaping every corner of every industry around the world. Without our customers, who are building the future on our platform, there would be no Google Cloud. In this regul
arXiv:2604.12376v1 Announce Type: cross Abstract: When LLM conversations grow beyond the context window, old content must be evicted -- but how does the model recover it when needed? We propose cooper
arXiv:2603.20475v3 Announce Type: replace Abstract: Standard attribution heatmaps show where a vision-language model (VLM) focuses, but they do not reveal whether the recovered evidence is organized b
arXiv:2511.19820v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or docum
arXiv:2604.12551v1 Announce Type: new Abstract: Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, h
arXiv:2604.12967v1 Announce Type: new Abstract: Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches
arXiv:2506.23104v2 Announce Type: replace Abstract: Interactive segmentation (IS) allows users to iteratively refine object boundaries with minimal cues, such as positive and negative clicks. While th
arXiv:2604.12424v1 Announce Type: cross Abstract: Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence.
arXiv:2604.12944v1 Announce Type: cross Abstract: Despite significant progress in video-language modeling, hallucinations remain a persistent challenge in Video Large Language Models (Vid-LLMs), refer
arXiv:2511.00710v4 Announce Type: replace Abstract: Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribut
arXiv:2604.12813v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new
arXiv:2604.12948v1 Announce Type: new Abstract: LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-
arXiv:2603.07083v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract repres
arXiv:2604.12403v1 Announce Type: new Abstract: Test-Time Prompt Tuning (TPT) adapts vision-language models using augmented views, but its effectiveness is hindered by the challenge of determining whi
arXiv:2509.19695v3 Announce Type: replace-cross Abstract: Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic dialog contexts, leading to inefficient
arXiv:2604.12579v1 Announce Type: new Abstract: Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, provid
arXiv:2604.12592v1 Announce Type: new Abstract: This paper presents our approach to the NTIRE 2026 3D Restoration and Reconstruction Challenge (Track 1), which focuses on reconstructing high-quality 3
arXiv:2604.12737v1 Announce Type: cross Abstract: While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs).
arXiv:2602.13851v3 Announce Type: replace-cross Abstract: Formal specifications are crucial for building verifiable and dependable software systems, yet generating accurate and verifiable specificatio
arXiv:2510.09536v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in multilingual, real-world applications with user inputs -- naturally introducing typographi
arXiv:2604.12559v1 Announce Type: new Abstract: Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grain
arXiv:2604.11929v1 Announce Type: new Abstract: Our ability to predict, control, and ultimately understand complex systems rests on discovering the equations that govern their dynamics. Identifying th
arXiv:2604.12656v1 Announce Type: cross Abstract: End-to-end diffusion planning has shown strong potential for autonomous driving, but the physical feasibility of generated trajectories remains insuff
arXiv:2504.06983v3 Announce Type: replace Abstract: Hierarchical inductive biases are hypothesized to promote generalizable policies in reinforcement learning, as demonstrated by explicit hyperbolic l
arXiv:2604.12508v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine
arXiv:2604.12147v1 Announce Type: cross Abstract: Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed
arXiv:2604.12344v1 Announce Type: cross Abstract: The exponential growth of data from modern radio telescopes presents a significant challenge to traditional single-pulse search algorithms, which are
arXiv:2604.12351v1 Announce Type: new Abstract: Automated diagnosis based on color fundus photography is essential for large-scale glaucoma screening. However, existing deep learning models are typica
arXiv:2604.12306v1 Announce Type: cross Abstract: Climate decision-making in the Gulf increasingly demands systems that can translate heterogeneous scientific and policy evidence into actionable guida
arXiv:2604.12336v1 Announce Type: cross Abstract: Streaming Data-Driven Optimization (SDDO) problems arise in many applications where data arrive continuously and the optimization environment evolves
arXiv:2604.12803v1 Announce Type: new Abstract: Neuromorphic vision sensors offer low latency and high dynamic range, but their deployment in public spaces raises severe data protection concerns. Rece
arXiv:2604.13030v1 Announce Type: new Abstract: While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless
arXiv:2410.23728v3 Announce Type: replace Abstract: With the increasing quality and spread of LLM assistants, the amount of generated content is growing rapidly. In many cases and tasks, such texts ar
arXiv:2604.11924v1 Announce Type: new Abstract: While LLMs hold significant potential to transform scientific research, we advocate for their use to augment and empower researchers rather than to auto
arXiv:2604.11810v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number
arXiv:2604.02830v2 Announce Type: replace Abstract: Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsibl
arXiv:2604.12929v1 Announce Type: new Abstract: We present Grasp in Gaussians (GraG), a fast and robust method for reconstructing dynamic 3D hand-object interactions from a single monocular video. Unl
arXiv:2511.05477v2 Announce Type: replace Abstract: Medical image segmentation demands models that achieve high accuracy while maintaining computational efficiency and clinical interpretability. While