Knowledge catalogue
arXiv:2605.00553v1 Announce Type: new Abstract: Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effec
arXiv:2605.00206v1 Announce Type: cross Abstract: Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and lea
arXiv:2605.00684v1 Announce Type: new Abstract: Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. R
arXiv:2503.10990v2 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying th
arXiv:2603.18413v3 Announce Type: replace-cross Abstract: A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating multiple analysis
arXiv:2603.28980v2 Announce Type: replace Abstract: The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with
arXiv:2605.00471v1 Announce Type: new Abstract: Robots operating in open, unstructured real-world environments must rely on onboard visual perception while autonomously moving across different locatio
arXiv:2512.01116v3 Announce Type: replace Abstract: The integration of histology images and gene profiles has shown great promise for improving survival prediction in cancer. However, current approach
arXiv:2605.00318v1 Announce Type: new Abstract: Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented gen
arXiv:2605.00557v1 Announce Type: new Abstract: Scientific discovery is an extended process of ideation--surveying prior work, forming hypotheses, and refining reasoning--yet existing approaches treat
arXiv:2509.23330v3 Announce Type: replace Abstract: Large language models (LLMs) have achieved significant advancements in reasoning capabilities through reinforcement learning (RL) via environmental
arXiv:2605.00033v1 Announce Type: cross Abstract: Remote and webcam-based eye tracking in multi-line reading suffers from various noise factors and layout ambiguity, precisely where real-time reading
arXiv:2605.00506v1 Announce Type: new Abstract: We model utterance production as probabilistic cost-sensitive choice over contextual alternatives, using information-theoretic notions of cost. We disti
arXiv:2507.09001v3 Announce Type: replace-cross Abstract: Machine learning (ML) models for electronic structure typically rely on large datasets generated by computationally expensive Kohn-Sham densit
arXiv:2511.03928v5 Announce Type: replace Abstract: We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task p
arXiv:2605.00261v1 Announce Type: new Abstract: Legged robots maintain dynamic feasibility through multicontact interactions with terrain. Learned foothold prediction can provide feasibility-aware cos
arXiv:2605.00140v1 Announce Type: cross Abstract: We present Activation Residual Hessian Quantization (ARHQ), a post-training weight splitting method designed to mitigate error propagation in low-bit
arXiv:2605.00738v1 Announce Type: new Abstract: With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical dat
arXiv:2605.00536v1 Announce Type: cross Abstract: Scaling laws for Large Language Models (LLMs) establish that model quality improves with computational scale, yet edge deployment imposes strict const
arXiv:2601.09896v4 Announce Type: replace-cross Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed 'aesthetic' is inextric
arXiv:2511.07756v4 Announce Type: replace Abstract: Diffusion models initialize generation from an isotropic Gaussian latent, yet changing only the random seed can substantially alter prompt faithfuln
arXiv:2605.00445v1 Announce Type: new Abstract: Large Language Models have achieved remarkable success and are increasingly deployed in critical applications involving tabular data, such as Table Ques
arXiv:2512.19927v2 Announce Type: replace Abstract: Seismology faces fundamental challenges in state forecasting and reconstruction (e.g., earthquake early warning and ground motion prediction) and ma
arXiv:2603.17837v3 Announce Type: replace-cross Abstract: During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal c
arXiv:2605.00754v1 Announce Type: cross Abstract: Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time sc
arXiv:2605.00438v1 Announce Type: cross Abstract: Long-horizon robotic manipulation requires plans that are both logically coherent and geometrically grounded. Existing Vision-Language-Action policies
arXiv:2602.06037v4 Announce Type: replace Abstract: Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However
arXiv:2506.11989v3 Announce Type: replace Abstract: Test-time scaling offers a promising way to improve the reasoning performance of vision-language large models (VLLMs) without additional training. I
arXiv:2605.00362v1 Announce Type: new Abstract: Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predic
arXiv:2605.00015v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TS
arXiv:2512.04694v3 Announce Type: replace Abstract: Effective earthquake risk reduction relies on accurate site-specific evaluations, which require models capable of representing the influence of loca
arXiv:2605.00143v1 Announce Type: new Abstract: Humor is a fundamental cognitive phenomenon in which humans derive pleasure from the expectation violations and their resolution, exemplifying the brain
arXiv:2605.00300v1 Announce Type: cross Abstract: Public inference benchmarks compare AI systems at the model and provider level, but the unit at which deployment decisions are actually made is the en
arXiv:2602.03216v2 Announce Type: replace Abstract: The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods
arXiv:2505.11329v5 Announce Type: replace-cross Abstract: Distributed inference of large language models (LLMs) using tensor parallelism can introduce communication overheads of 20% even over GPUs con
arXiv:2508.04086v2 Announce Type: replace Abstract: Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS
arXiv:2605.00182v1 Announce Type: new Abstract: Proteins are shaped by gradual evolution under biophysical and functional constraints. Protein language models learn rich evolutionary constraints from
arXiv:2605.00390v1 Announce Type: new Abstract: We present extit{CluProp}, a novel framework that reimagines varied-density clustering in high-dimensional spaces as a label propagation process over ne
arXiv:2605.00488v1 Announce Type: new Abstract: In multi-armed bandits, the most-explored arms are the most informative, while reward maximization typically pulls only the best arm. We study the trade
arXiv:2605.00414v1 Announce Type: new Abstract: Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work u
arXiv:2605.00297v1 Announce Type: cross Abstract: Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE heade
arXiv:2510.21141v2 Announce Type: replace-cross Abstract: Internet speed tests are indispensable for users, ISPs, and policymakers, but their static flooding-based design imposes growing costs: a sing
arXiv:2605.00052v1 Announce Type: new Abstract: Hybrid-capture novel view synthesis combines images at substantially different camera distances (e.g., aerial drone and ground-level views). Standard 3D
arXiv:2511.05582v2 Announce Type: replace Abstract: Real-Time Auction (RTA) Interception aims to filter out invalid or irrelevant traffic to enhance the integrity and reliability of downstream data. H
arXiv:2509.24255v2 Announce Type: replace-cross Abstract: As virtual reality (VR) becomes widespread, head and hand motion data captured by consumer systems has become substantially more common. Howev
arXiv:2605.00365v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved substantial gains in single-attempt accuracy (Pass@1) on reasoning tasks, yet often
arXiv:2605.00658v1 Announce Type: new Abstract: Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often tr
arXiv:2605.00638v1 Announce Type: new Abstract: Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy ri
arXiv:2605.00364v1 Announce Type: new Abstract: Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existin
arXiv:2510.00072v2 Announce Type: replace Abstract: Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. W
arXiv:2605.00719v1 Announce Type: new Abstract: Unsupervised deraining has attracted attention for its ability to learn the real-world distribution of rain without paired supervision. However, the lac
arXiv:2605.00793v1 Announce Type: cross Abstract: With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising
arXiv:2312.12339v3 Announce Type: replace Abstract: Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose exti
arXiv:2602.04349v2 Announce Type: replace Abstract: 3D editing has emerged as a critical research area to provide users with flexible control over 3D assets. While current editing approaches predomina
arXiv:2605.00538v1 Announce Type: new Abstract: Blood vessel segmentation and -tracing are essential tasks in many medical imaging applications. Although numerous methods exist, the prevailing segment
arXiv:2506.11991v3 Announce Type: replace-cross Abstract: In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which
arXiv:2603.22285v2 Announce Type: replace Abstract: Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identify
arXiv:2605.00116v1 Announce Type: new Abstract: In this article, we introduce ViLegalNLI, the first large-scale Vietnamese Natural Language Inference (NLI) dataset specifically constructed for the leg
arXiv:2605.00219v1 Announce Type: new Abstract: We present VkSplat, a high-performance, cross-vendor 3D Gaussian Splatting (3DGS) training pipeline implemented fully in Vulkan compute, addressing perf
arXiv:2505.03500v5 Announce Type: replace Abstract: Vision-language-action models (VLAs) often achieve high performance on demonstrated tasks but struggle significantly when required to extrapolate, c