Knowledge catalogue
arXiv:2609.34497v1 Announce Type: new Abstract: Flow policies can model rich action distributions, but their iterative sampling limits decision speed. Adjoint matching uses the critic's action gradien
arXiv:2609.33088v1 Announce Type: new Abstract: Traditional change detection (CD) identifies changes between bi-temporal remote sensing images, while semantic change detection (SCD) assigns predefined
arXiv:2609.31668v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) process multimodal inputs by converting text, images, and videos into token sequences that are subsequently pro
arXiv:2609.33848v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model-
arXiv:2510.13854v2 Announce Type: replace-cross Abstract: We introduce Rule-to-Tag (R2T), a framework that turns linguistic rules into the training signal for neural sequence taggers in low-resource l
arXiv:2609.32836v1 Announce Type: cross Abstract: Radiomap blind prediction aims to infer radiomaps from observable representations of the propagation environment and base station configuration withou
arXiv:2609.34367v1 Announce Type: new Abstract: Learned image codecs (LICs) achieve high reconstruction quality, but their decoding speed is often insufficient for immersive virtual reality (VR). Gaus
arXiv:2609.32155v1 Announce Type: new Abstract: Sequential manipulation requires a robot to track what has already happened, even when the current scene no longer reveals it. Policies with explicit hi
arXiv:2609.31927v1 Announce Type: cross Abstract: MathNet-Retrieve asks a retriever to find, for a math problem, a document stating the same problem. An LLM under one fixed prompt writes each gold doc
arXiv:2609.34032v1 Announce Type: new Abstract: A manga reader meets a character on one page and knows them on sight a hundred pages later, without ever being handed a cast list. Re-identifying comic
arXiv:2609.35405v1 Announce Type: new Abstract: Pretrained 2D foundation models offer a practical alternative to dedicated 3D pretraining for brain structural magnetic resonance imaging (sMRI), but th
arXiv:2609.31771v1 Announce Type: new Abstract: Many planning and control tasks for tendon-driven continuum robots (TDCRs) require the complete Cartesian backbone geometry. We present a reduced Cartes
arXiv:2609.34904v1 Announce Type: new Abstract: Graph neural networks (GNNs) need to exploit improved message passing without surrendering control over predictions already trusted in deployment. We in
arXiv:2609.32516v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) process large volumes of alerts daily. Alert triage prioritizes high-risk threats while reducing manual review of b
arXiv:2609.35078v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models for autonomous driving rely heavily on successful expert demonstrations, leaving model-specific failures underexploi
arXiv:2609.32669v1 Announce Type: cross Abstract: Attention weights depend on token counts, which change with the representation of a signal. We study refinement symmetry: splitting a representation w
arXiv:2609.32068v1 Announce Type: new Abstract: Motion retargeting transfers motion across characters with different skeletal structures while preserving semantic intent and physical plausibility. Des
arXiv:2609.34587v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to post-train vision-language models for image-to-code generation, such as generating SVG code from a refere
arXiv:2609.31816v1 Announce Type: new Abstract: What should a compressed representation preserve when the information of interest lies in relationships among elements rather than in the elements thems
We have released Qwen3.8-Flash-Next quantized with GSQ and RCO, together with a second, capability-targeted build in which half of the model's experts have been removed. Flash-Next is a sparse mixture
arXiv:2609.33412v1 Announce Type: new Abstract: Despite rapid progress in vision-language-action (VLA) models, existing reasoning paradigms still face a fundamental state-representation mismatch in op
arXiv:2609.33687v1 Announce Type: new Abstract: Onboard satellite models often require frequent updates, but the weights adapted to earlier data distributions can quickly become outdated. However, upd
arXiv:2609.35469v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action (VLA) models offer a scalable path to robot learning, yet existing action tokenizers treat tokenization as a com
arXiv:2609.34563v1 Announce Type: new Abstract: Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather th
arXiv:2609.32899v1 Announce Type: new Abstract: Hyperbolic space can embed intrinsic hierarchies in data with low distortion due to the exponential growth of volume with distance from the origin. Howe
arXiv:2609.34566v1 Announce Type: new Abstract: Predicting observed dynamics does not establish recovery of the underlying physical mechanism. Can machine learning retrace the hidden-state reasoning b
arXiv:2609.32590v1 Announce Type: new Abstract: Work on memory for multimodal agents optimizes what is written, updated and retrieved. Between retrieval and the answer, however, is a stage that multim
arXiv:2609.32749v1 Announce Type: cross Abstract: Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising que
arXiv:2609.32756v1 Announce Type: new Abstract: Foundation models are rarely used as generic, frozen feature extractors; instead, they are fine-tuned for the target downstream application. This practi
arXiv:2609.32984v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a promising path for overcoming the limited visual capability of current medical imaging agents. Yet applying RS
arXiv:2609.34004v1 Announce Type: new Abstract: Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information
arXiv:2609.32236v1 Announce Type: new Abstract: Generative models, such as diffusion and flow-based models, have shown strong promise for robot policy learning by capturing complex and multimodal acti
arXiv:2609.32250v1 Announce Type: new Abstract: Sign-language interpretation in public communication relies on qualified professional interpreters and can be difficult to scale, motivating robotic sig
arXiv:2609.35311v1 Announce Type: new Abstract: Action-conditioned video world models predict future robot interactions from multiple cameras, yet their outputs remain disparate video collections rath
arXiv:2609.32500v1 Announce Type: new Abstract: Many real-world time series data exhibit structural properties at multiple scales, from short, recurring units to complex sequences composed of these un
arXiv:2609.32821v1 Announce Type: cross Abstract: Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mi
arXiv:2609.31698v1 Announce Type: new Abstract: Most existing MEG and EEG (M/EEG) visual decoding methods align brain signals with a single global embedding extracted from a pretrained visual encoder,
arXiv:2603.09160v2 Announce Type: replace Abstract: Dense image captioning is critical for vision-language pretraining and for text-to-image generation, but scaling expert-quality annotations is prohi
arXiv:2606.14586v2 Announce Type: replace Abstract: Self-supervised learning can learn useful representations from unlabeled images. Yet these representations remain largely opaque, making it difficul
arXiv:2609.33640v1 Announce Type: new Abstract: Molecular multimodal models support diverse understanding and generation tasks but may introduce safety vulnerabilities when handling hazardous molecule
arXiv:2609.32755v1 Announce Type: cross Abstract: Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current
arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun
arXiv:2609.32108v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models leverage large-scale pretraining to ultimately achieve generalist manipulation. Deployed VLA policies must support c
arXiv:2609.33641v1 Announce Type: cross Abstract: Several businesses apply maintenance, repair, and overhaul (MRO) principles to the life-cycle of their existing products. In cases like casted gas tur
arXiv:2609.33667v1 Announce Type: new Abstract: Attributing and controlling model behavior during training requires identifying each example's contribution quickly enough to act before the next update
arXiv:2609.35333v1 Announce Type: new Abstract: Algorithm Distillation (AD) has demonstrated the remarkable ability of Transformers to perform in-context reinforcement learning without explicit weight
arXiv:2609.33218v1 Announce Type: new Abstract: Visual world models enable robotic planning by predicting future observations, but dense latent-state propagation and sample-intensive trajectory optimi
arXiv:2609.34970v1 Announce Type: new Abstract: Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated
arXiv:2609.34277v1 Announce Type: new Abstract: Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pat
arXiv:2609.32456v1 Announce Type: new Abstract: World modeling under partial observation requires reasoning about the complete worlds that remain compatible with limited visual evidence. Occluded obje
arXiv:2603.02772v2 Announce Type: replace Abstract: Motion planners tuned under nominal conditions can fail when execution conditions change. Existing differentiable adaptation methods provide efficie
arXiv:2609.32340v1 Announce Type: new Abstract: Reinforcement Learning (RL) has proven effective in aligning flow-based generative models with human preferences. Recently, Flow-GRPO has emerged as an
arXiv:2609.34604v1 Announce Type: new Abstract: World models learn environment dynamics from interaction experience. These dynamics depend on the current state and actions, as well as on properties th
arXiv:2609.35576v1 Announce Type: cross Abstract: Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and
arXiv:2609.32546v1 Announce Type: new Abstract: Large language models can generate several records within one autoregressive completion, making earlier answers available as context for later records.
arXiv:2609.31940v1 Announce Type: new Abstract: Multi-objective Bayesian optimization (MOBO) is commonly approached through specialized acquisition functions or scalarization schemes designed to expli
arXiv:2609.34743v1 Announce Type: new Abstract: Planetary robotics is an important enabler of scientific exploration in environments where direct human-in-the-loop operation is costly, hazardous, or i
arXiv:2609.32231v1 Announce Type: new Abstract: Human motion prediction requires diverse future trajectories that remain consistent with observed motion and the articulated physical structure of the b
arXiv:2609.34335v1 Announce Type: new Abstract: Achieving high-quality, cinematic results in text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrati
arXiv:2609.32847v1 Announce Type: cross Abstract: We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance. SOW replaces the L^p norm in SW wit