Knowledge catalogue
arXiv:2609.34426v1 Announce Type: new Abstract: This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an offline
arXiv:2609.33269v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly generate video and robot actions through iterative diffusion and perform strongly in robotic manipulation. However,
arXiv:2609.34842v1 Announce Type: new Abstract: Existing multimodal time series foundation models (TSFMs) typically model heterogeneous modalities through largely shared mechanisms, overlooking the di
arXiv:2609.34718v1 Announce Type: new Abstract: Reinforcement learning (RL) changes not only what language models say, but also how much they say, often increasing response length at the cost of token
arXiv:2601.04301v3 Announce Type: replace Abstract: As frontier AI systems are pretrained on web-scale data, test set contamination has become a critical concern for accurately assessing their capabil
arXiv:2609.35349v1 Announce Type: new Abstract: The evaluation cost of transformers with softmax attention scales quadratically with sequence length. Kernel attention addresses this by replacing softm
arXiv:2609.33097v1 Announce Type: new Abstract: Recent large-scale Vision-and-Language Navigation (VLN) models deliver strong accuracy but remain costly to deploy due to their large parameter counts a
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:2609.33351v1 Announce Type: cross Abstract: Fidelity-based quantum retrieval ranks candidates by the fidelity between query and archive states. Applying a shared input-independent unitary after
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:2609.32757v1 Announce Type: cross Abstract: VLM bounding-box localization is both language generation and spatial commitment. Parseable fields such as bbox_2d make localization easy to score, bu
arXiv:2609.34567v1 Announce Type: new Abstract: This review examines the evolution of plant phenotyping from conventional manual trait measurement to high-throughput, robotic, and artificial intellige
arXiv:2609.34231v1 Announce Type: new Abstract: Metamaterials are artificially engineered structures whose mechanical and physical behaviors are strongly shaped by geometry rather than composition. Vo
arXiv:2511.20237v2 Announce Type: replace-cross Abstract: The Newton-Raphson (NR) method is widely used for solving power flow (PF) equations due to its quadratic convergence. However, its performance
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:2609.35764v1 Announce Type: new Abstract: Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientati
arXiv:2609.32460v1 Announce Type: new Abstract: Recent video generation models produce realistic videos and show potential as a foundation for world models. These advances create opportunities for gen
arXiv:2609.32263v1 Announce Type: new Abstract: Multimodal test-time adaptation (TTA) aims to adapt a pretrained multimodal model online to distribution shift across modalities using unlabeled test da
arXiv:2609.33020v1 Announce Type: new Abstract: Diffusion models achieve state-of-the-art results across multiple tasks. However, in inverse problems, standard initialization from pure Gaussian noise
arXiv:2609.34701v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate enterprise workflows involving multiple specialized agents, external tools, and long-runni
arXiv:2609.31932v1 Announce Type: cross Abstract: Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental mo
arXiv:2609.35433v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) frequently reuses rollouts across multiple policy updates, increasing the mismatch between the cur
arXiv:2609.33944v1 Announce Type: new Abstract: Jointly generating future video and actions has become a standard recipe for world-action models, and the strongest systems denoise the two streams on s
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:2609.35686v1 Announce Type: new Abstract: Mechanistic interpretability (MI) aims to explain a model's behaviour through analyzing its internal computations; circuit-based explanations aim to iso
arXiv:2609.35394v1 Announce Type: new Abstract: Video Large Language Models (Video LLMs) have achieved remarkable progress in video understanding, but their inference efficiency is constrained by the
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:2609.32756v1 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:2609.34863v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have approached image segmentation by reasoning about visual content and predicting target locations. Their gen
arXiv:2609.33716v1 Announce Type: new Abstract: Diffusion-based unsupervised domain adaptation (UDA) improves cross-domain transfer by generating target-specific synthetic data for downstream adaptati
arXiv:2609.34652v1 Announce Type: new Abstract: Medical time series (MedTS) underpin many clinical classification tasks, yet existing methods usually represent them only as numerical sequences and und
arXiv:2609.33989v1 Announce Type: cross Abstract: Reward models (RMs) are a key component of large language model post-training, providing reward signals for subsequent reinforcement learning. However
arXiv:2609.32537v1 Announce Type: new Abstract: Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost
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:2609.34556v1 Announce Type: cross Abstract: Transformers process tokens without any inherent notion of order, making positional encoding a fundamental requirement rather than an architectural re
arXiv:2609.34326v1 Announce Type: new Abstract: Large Language Model (LLM) routers commonly rely on neural query embeddings, with larger encoders expected to better capture query intent and difficulty
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:2609.33337v1 Announce Type: new Abstract: Online safe reinforcement learning (RL) seeks policies that maximize reward while satisfying safety constraints. A popular line of research in safe RL r
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:2609.32108v1 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:2609.32183v1 Announce Type: new Abstract: High-resolution plant imaging enables detailed characterization of plant morphology, but dense scientific analysis remains limited by costly pixel-level
arXiv:2609.33399v1 Announce Type: new Abstract: In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and a te
arXiv:2609.33780v1 Announce Type: new Abstract: Verified solutions are not equally useful for preparing reasoning models for reinforcement learning (RL). We present a comprehensive study of route dive
arXiv:2609.32689v1 Announce Type: new Abstract: LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and gu
arXiv:2609.35225v1 Announce Type: cross Abstract: Sign language translation and generation share the goal of bidirectional alignment between text and sign representations. However, existing approaches
arXiv:2609.32691v1 Announce Type: cross Abstract: LLM agents that invoke privileged tools are vulnerable to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved dat
arXiv:2609.33947v1 Announce Type: cross Abstract: Diffusion language models (DLMs) promise fast parallel generation, yet high-quality samples often require large number of refinement steps, which dimi
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:2609.33112v1 Announce Type: new Abstract: Gaussian process stochastic differential equations (GP-SDEs) provide a flexible Bayesian model for unknown continuous-time state dynamics with uncertain
arXiv:2609.33051v1 Announce Type: new Abstract: Hybrid-attention models replace most softmax attention layers with linear attention, reducing KV-cache growth and enabling larger decode batches where r
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:2609.34117v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traf
arXiv:2609.33575v1 Announce Type: new Abstract: Vision-Language-Action models are increasingly effective for robotic manipulation, yet most predict actions directly from current observations without e
arXiv:2603.00717v3 Announce Type: replace Abstract: Recent advances in generative models have exposed a fundamental weakness of image fake detectors: they often fail to generalize to unseen synthesis
arXiv:2609.34707v1 Announce Type: new Abstract: Object navigation requires an embodied agent to find an object in an unseen environment under partial observability and a limited motion budget. Existin
arXiv:2609.32143v1 Announce Type: new Abstract: Pre-training Graph Neural Networks (GNNs) via self-supervised learning has become a dominant paradigm, yet efficiently adapting frozen encoders remains
arXiv:2609.33462v1 Announce Type: new Abstract: Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use of Mu
arXiv:2609.35097v1 Announce Type: new Abstract: Spiking neural networks (SNNs) offer an energy-efficient paradigm for time-series forecasting through spike-driven computation. However, recent SNN fore
arXiv:2609.35497v1 Announce Type: new Abstract: Long video understanding relies on video memory to overcome the context limits of multimodal large language models. Existing methods follow a build-then
arXiv:2609.34019v1 Announce Type: new Abstract: In many high-stakes applications, machine learning is dominated by black-box models that require post hoc explanations to justify their predictions. The