Knowledge catalogue
arXiv:2606.04592v1 Announce Type: cross Abstract: LLM-based digital twins promise to scale and accelerate market research, but most published twins are either coarse persona bots conditioned on a few
arXiv:2512.04668v4 Announce Type: replace-cross Abstract: Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, yet its effects remain poorly quantified. We introdu
arXiv:2606.04222v1 Announce Type: new Abstract: Prosthetic socket fitting remains largely manual and iterative, and objective fit metrics are still limited. Part of the challenge is the lack of long-t
arXiv:2606.04658v1 Announce Type: cross Abstract: Optimizing urban layouts for climate adaptation requires balancing building density with cold-air ventilation. Because physics-based climate simulatio
arXiv:2606.03675v1 Announce Type: new Abstract: Methane is a potent greenhouse gas, and detecting leaks early via hyperspectral satellite imagery can help climate change mitigation efforts. Meanwhile,
arXiv:2606.02670v1 Announce Type: cross Abstract: Many recent multivariate time series anomaly detection (MT-SAD) models incorporate cross-channel modeling, under the implicit assumption that the stru
arXiv:2606.03070v1 Announce Type: cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, bu
arXiv:2606.02724v1 Announce Type: cross Abstract: Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric
arXiv:2606.03920v1 Announce Type: new Abstract: Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacit
arXiv:2606.03879v1 Announce Type: cross Abstract: As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a
arXiv:2606.03259v1 Announce Type: new Abstract: Translation quality depends on purpose: the same source text demands different translations depending on audience, tone, and communicative intent. Yet M
arXiv:2606.02609v1 Announce Type: cross Abstract: Activation Oracles (AOs) are promising methods for interpreting residual stream activations. However, current AOs face important issues, such as hallu
arXiv:2603.05207v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge. However, existing vector-based method
arXiv:2606.02800v1 Announce Type: cross Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences
arXiv:2602.06219v2 Announce Type: replace-cross Abstract: World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex
arXiv:2511.19995v2 Announce Type: replace Abstract: Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would
arXiv:2606.03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficienc
arXiv:2606.02912v1 Announce Type: cross Abstract: Forecasting seismic waveforms beyond observed data remains challenging due to the nonlinear, dispersive, and multi-scale nature of seismic wave propag
arXiv:2606.03601v1 Announce Type: cross Abstract: While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rej
arXiv:2606.03103v1 Announce Type: new Abstract: Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop
arXiv:2606.03578v1 Announce Type: new Abstract: Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstructi
arXiv:2606.03142v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over
arXiv:2606.02939v1 Announce Type: new Abstract: Interpretable brain-computer interface classifiers that generalize across subjects without calibration remain an open challenge. We test whether prototy
arXiv:2606.03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversa
arXiv:2606.03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, wher
arXiv:2606.03821v1 Announce Type: new Abstract: Active learning is now standard practice in labeling ecological data, enabling ecologists to quickly process large volumes of field data to understand a
arXiv:2606.03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps. Real-world benchmarks off
arXiv:2606.03216v1 Announce Type: new Abstract: We study preference alignment for image inpainting. Rather than proposing yet another method, we revisit the problem from first principles and reassess
arXiv:2606.02860v1 Announce Type: cross Abstract: Catastrophic forgetting is often framed as a representational problem: after sequential training, a model appears to lose the features that supported
arXiv:2606.03761v1 Announce Type: new Abstract: Frame analysis of migration news is a socially consequential task: media scholars and researchers who study how migration is narrated need tools that ar
arXiv:2606.02764v1 Announce Type: new Abstract: Satellite-derived bathymetry (SDB) from multispectral imagery is cost-effective but scales poorly across regions, especially in optically complex coasta
arXiv:2606.03165v1 Announce Type: cross Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment). Research, mostly on Scientific Englis
arXiv:2606.02741v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in sustainability-related decision support, reporting, and public communication, yet little systemati
arXiv:2606.03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The har
arXiv:2606.03523v1 Announce Type: cross Abstract: Early attribution of Advanced Persistent Threat (APT) activity can help defenders prioritise investigation, select countermeasures, and reduce the imp
arXiv:2510.23216v4 Announce Type: replace Abstract: While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the
arXiv:2606.03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts. Chunk-wise memory agents address this issue by
arXiv:2606.03168v1 Announce Type: new Abstract: While instruction-based video editing has seen significant progress, joint audio-visual editing remains constrained by the absence of dedicated datasets
arXiv:2606.03773v1 Announce Type: new Abstract: High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their Engl
arXiv:2308.07867v4 Announce Type: replace-cross Abstract: The absence of formal performance guarantees in machine learning (ML) has limited its adoption for safety-critical power system applications,
arXiv:2606.03246v1 Announce Type: new Abstract: The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training dat
arXiv:2606.03890v1 Announce Type: new Abstract: Multimodal agents in robotics, AR, and autonomous driving must reason about places and layouts from continuous egocentric streams, often using evidence
arXiv:2601.12247v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) a
arXiv:2502.02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings. Yet
arXiv:2606.03889v1 Announce Type: new Abstract: Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real develop
arXiv:2512.07394v2 Announce Type: replace Abstract: We introduce the task of Reconstructing Objects along Hand Interaction Timelines (ROHIT). We first define the Hand Interaction Timeline (HIT) from a
arXiv:2606.03421v1 Announce Type: new Abstract: Specular glare on reflective floors, glass boundaries, and glossy indoor surfaces frequently corrupts active-stereo RGB-D depth measurements, producing
arXiv:2606.03465v1 Announce Type: cross Abstract: Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged
arXiv:2606.03648v1 Announce Type: cross Abstract: Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety. Previ
arXiv:2606.03517v1 Announce Type: cross Abstract: Training quantum neural networks (QNNs) on quantum hardware is currently bottlenecked by the cost of gradient estimation: standard parameter-shift met
arXiv:2505.08222v3 Announce Type: replace-cross Abstract: Autonomous vehicles (AVs) offer a cost-effective solution for scientific missions such as underwater tracking. Reinforcement learning (RL) has
arXiv:2606.03963v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use
arXiv:2606.02664v1 Announce Type: cross Abstract: Latent state-space models are widely used to study partially observed dynamical systems, yet most formulations assume that process variability is inde
arXiv:2606.03250v1 Announce Type: new Abstract: Digital healthcare generates vast amounts of clinical text that can support AI-assisted applications, yet German biomedical language models remain limit
arXiv:2606.02894v1 Announce Type: new Abstract: Small edge devices such as IoT surveillance nodes and search-and-rescue (SAR) platforms are increasingly expected to run computer vision locally. On ult
arXiv:2606.02806v1 Announce Type: new Abstract: We introduce Padyam2Gadyam, a dataset for the task of poem-to-prose translation from 13th-17th Century Telugu Classical Poetry to contemporary Telugu an
arXiv:2606.03629v1 Announce Type: new Abstract: Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently,
arXiv:2303.15619v2 Announce Type: replace-cross Abstract: The choice of which tokens to mask is a central, under-examined design decision in masked language modeling (MLM). Standard pretraining masks
arXiv:2512.22539v2 Announce Type: replace-cross Abstract: While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively und
arXiv:2606.01973v1 Announce Type: cross Abstract: Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes. While recent methods have m