Knowledge catalogue
arXiv:2607.23700v1 Announce Type: new Abstract: Multimodal large language models exhibit capabilities on reasoning tasks, yet often produce flawed intermediate steps while yielding correct final answe
arXiv:2607.23193v1 Announce Type: new Abstract: Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show
arXiv:2607.23310v1 Announce Type: cross Abstract: We study an online variant of discrete fair division under generalized assignment budget constraints. Goods arrive one at a time and must be assigned
arXiv:2607.22621v1 Announce Type: new Abstract: While large language models (LLMs) enable strong question answering (QA), budgeted deployment is complicated by nondeterminism and heterogeneous resourc
arXiv:2607.22805v1 Announce Type: cross Abstract: We propose OrchNAS, an energy-aware, personalised, federated edge intelligence framework that leverages a Neural Architecture Search Service to automa
arXiv:2607.24296v1 Announce Type: new Abstract: Diffusion Policies (DPs) are able to perform complex manipulation tasks. However, DPs are typically trained by minimizing a denoising objective, which p
arXiv:2607.23447v1 Announce Type: new Abstract: Predicting cellular responses to unseen chemical perturbations is challenging due to unknown targets and mechanisms, high-dimensional expression respons
arXiv:2411.00967v2 Announce Type: replace Abstract: The future of agriculture is intertwined with automation. Accurate fruit detection, yield estimation, and harvest time prediction are crucial for ef
arXiv:2607.24513v1 Announce Type: new Abstract: Transformer architectures have attracted increasing attention for solving partial differential equations (PDEs), owing to their flexibility in handling
arXiv:2607.24052v1 Announce Type: new Abstract: High-curvature regions in 3D point clouds encapsulate critical fine-grained geometric semantics yet exhibit a distinct long-tail sparsity in their spati
arXiv:2607.22818v1 Announce Type: cross Abstract: We introduce a new class of fully-quantum Metropolis walks in which both the proposal and acceptance steps are intrinsically quantum. Unlike standard
arXiv:2607.22634v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, generating tokens in parallel. This makes t
arXiv:2607.22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing traject
arXiv:2607.22549v1 Announce Type: new Abstract: Hybrid quantum-classical protein structure prediction depends strongly on Hamiltonian penalty weights, yet existing lattice-based workflows typically fi
arXiv:2607.22997v1 Announce Type: cross Abstract: Physical AI -- the integration of large vision-language-action (VLA) models with embodied agents that act in the real world -- has emerged as the next
arXiv:2607.23927v1 Announce Type: new Abstract: A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts. In humans, this capacity i
arXiv:2607.14178v2 Announce Type: replace Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated resea
arXiv:2607.23019v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not
arXiv:2601.02580v2 Announce Type: replace-cross Abstract: Traditional methods for determining assessment item parameters, such as difficulty and discrimination, rely heavily on expensive field testing
arXiv:2607.22570v1 Announce Type: new Abstract: Auditing a new language model usually means relearning and reinterpreting its internal features from scratch. We propose a reference feature atlas: a sp
arXiv:2607.22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk. Existi
arXiv:2601.14032v2 Announce Type: replace Abstract: Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-qua
arXiv:2607.23468v1 Announce Type: new Abstract: Real-time 6-DoF object pose tracking is essential for many robotics applications, and several approaches exist. Yet even today's approaches remain unrel
arXiv:2502.16184v3 Announce Type: replace Abstract: The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems. While prior work has sought to cl
arXiv:2412.20541v2 Announce Type: replace Abstract: Memes act as cryptic tools for sharing sensitive ideas, often requiring contextual knowledge to interpret them correctly. It makes multimodal meme m
arXiv:2607.23238v1 Announce Type: new Abstract: Masked image modeling has become a dominant paradigm for SAR pre-training, yet the design of the reconstruction target remains fundamentally unsettled.
arXiv:2607.24112v1 Announce Type: new Abstract: We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal
arXiv:2607.22713v1 Announce Type: new Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historic
arXiv:2607.23125v1 Announce Type: new Abstract: Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks. Current post-training methods
arXiv:2512.12713v2 Announce Type: replace-cross Abstract: Control policies are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which require architecture selec
arXiv:2502.05925v2 Announce Type: replace-cross Abstract: Backpropagation (BP) has long been the predominant method for training neural networks due to its effectiveness. However, numerous alternative
arXiv:2607.24249v1 Announce Type: new Abstract: Standard depth sensors systematically fail on transparent surfaces, creating corrupted 3D maps and severe navigation hazards. While specialized hardware
arXiv:2607.24492v1 Announce Type: new Abstract: The goal of schema integration is, given a set of input schemata or tables, to derive a global, unified schema that is able to represent the concepts, a
arXiv:2607.24007v1 Announce Type: cross Abstract: We revisit contextual optimization from the perspective of policy class design. A desirable policy class should be expressive enough to learn rich con
The Information: Sources: Moonshot is seeking access to more Nvidia Blackwell chips to prepare for Kimi K4's development, after training K3 on Nvidia chips, including Blackwell — Beijing-based startup
arXiv:2607.22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing bench
arXiv:2607.24701v1 Announce Type: new Abstract: Missing modalities in RGBT tracking often lead to incomplete and unstable multimodal feature representations that greatly degrade the performance. Exist
arXiv:2607.23346v1 Announce Type: new Abstract: Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute s
arXiv:2607.22649v1 Announce Type: new Abstract: Following complex instructions with multiple explicit constraints remains a fundamental challenge for large language models (LLMs). Existing alignment m
arXiv:2607.22592v1 Announce Type: new Abstract: Graph-based retrieval-augmented generation (GraphRAG) grounds answers in structured knowledge, but current systems extract entities and relationships ex
arXiv:2603.27577v2 Announce Type: replace Abstract: Vision-Language Navigation (VLN) requires an embodied agent to navigate complex environments by following natural language instructions, which typic
arXiv:2607.23991v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements. However,
arXiv:2509.06278v4 Announce Type: replace Abstract: Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large lang
arXiv:2607.24611v1 Announce Type: new Abstract: Deep learning models have achieved state-of-the-art performance in several computer vision tasks. However, they experience severe performance degradatio
arXiv:2607.22807v1 Announce Type: cross Abstract: Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very signifi
arXiv:2607.22762v1 Announce Type: cross Abstract: Causal inference has become a central issue across various fields, including computer science, statistics, economics, education, healthcare, and medic
arXiv:2607.22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies
arXiv:2607.23404v1 Announce Type: new Abstract: Self-driving laboratories increasingly rely on multi-fidelity Bayesian optimization (MFBO) to balance cheap, approximate evaluations against scarce, exp
arXiv:2607.24215v1 Announce Type: new Abstract: Although general text-to-image models excel in open-domain generation, their performance degrades significantly in specialized downstream domains, parti
arXiv:2607.23434v1 Announce Type: cross Abstract: Unexpected shocks recur in global operations, requiring decision rules that adapt as market and operating conditions change. Many operational systems
arXiv:2512.24125v3 Announce Type: replace-cross Abstract: General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action executio
arXiv:2607.24338v1 Announce Type: new Abstract: Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without rely
arXiv:2602.19349v2 Announce Type: replace-cross Abstract: LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a c
arXiv:2509.06108v3 Announce Type: replace-cross Abstract: Graph drawing concerns the algorithmic visualization of graphs. A good drawing of a graph is easy to read and facilitates solving tasks on the
arXiv:2607.23198v1 Announce Type: new Abstract: We propose Variance-Preserving Orthogonal Selection (VPOS), a greedy framework for unsupervised feature selection that operates in the weighted PCA load
arXiv:2607.23006v1 Announce Type: cross Abstract: Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the suppo
arXiv:2607.22704v1 Announce Type: cross Abstract: Nuclear fusion has made significant progress in recent years and is expected to become one of the most important pathways to addressing global energy
arXiv:2607.22716v1 Announce Type: new Abstract: In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vuln
arXiv:2512.22342v5 Announce Type: replace Abstract: In most existing embodied navigation tasks, instructions are well-defined and unambiguous, such as instruction following and object searching. Under
arXiv:2607.23265v1 Announce Type: new Abstract: Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. Whil