Knowledge catalogue
arXiv:2605.30447v1 Announce Type: cross Abstract: Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making. While extensively stud
arXiv:2601.22412v2 Announce Type: replace Abstract: Video-based human movement analysis holds potential for movement assessment in clinical practice and research. However, the clinical implementation
arXiv:2605.30774v1 Announce Type: new Abstract: Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly i
arXiv:2605.31066v1 Announce Type: new Abstract: Recent aerial vision-language-action (VLA) models show promising single-UAV capabilities, such as tracking moving objects and navigating to language-spe
arXiv:2605.30983v1 Announce Type: new Abstract: Despite the remarkable success of multi-modal bird's-eye view (BEV) perception in autonomous driving, current systems exhibit a critical vulnerability:
arXiv:2605.30459v1 Announce Type: new Abstract: Large language models (LLMs) remain limited on tasks requiring indirect reasoning, cultural knowledge, and coordinated hypothesis testing. We investigat
arXiv:2605.30470v1 Announce Type: new Abstract: Graph Machine Learning as a Service (GMLaaS) platforms increasingly implement explainability interfaces to meet regulatory transparency requirements. Ho
arXiv:2605.30497v1 Announce Type: new Abstract: RAG-based legal assistants have been growing in popularity, but LLM hallucinations remain a key issue and potentially undermines justice. While benchmar
arXiv:2510.14904v3 Announce Type: replace-cross Abstract: Dense Video Object Captioning (DVOC) is the task of jointly detecting, tracking, and captioning object trajectories in a video, requiring the
arXiv:2510.22067v3 Announce Type: replace Abstract: Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior wor
arXiv:2605.30583v1 Announce Type: new Abstract: We present Caspar, a library that makes the power of modern GPUs more accessible in robotics and provides a state-of-the-art nonlinear GPU solver that c
arXiv:2602.02819v3 Announce Type: replace Abstract: Membership Inference Attacks (MIAs) aim to distinguish training points (members) from unseen data (non-members), and are widely used to quantify mem
arXiv:2605.30635v1 Announce Type: new Abstract: Inferring dynamics from population snapshots is a fundamental challenge in machine learning and biology. In scRNA-sequencing (scRNA-seq), destructive me
arXiv:2602.22968v3 Announce Type: replace Abstract: Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pur
arXiv:2605.30757v1 Announce Type: new Abstract: Chain-of-thought prompting and looped Transformers both give a fixed model more test-time computation, but they differ in what they remember. Chain-of-t
arXiv:2503.08679v5 Announce Type: replace Abstract: Recent studies indicate that when faced with explicit biases in prompts, models often omit mentioning these biases in their Chain-of-Thought (CoT) o
arXiv:2605.30748v1 Announce Type: cross Abstract: We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion d
arXiv:2605.31522v1 Announce Type: new Abstract: Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecul
arXiv:2605.31581v1 Announce Type: new Abstract: The same arguments often need to be evaluated under different external regimes. An agent with influence over the regime has a strategic lever that stand
arXiv:2603.23977v2 Announce Type: replace-cross Abstract: Deep networks often rely on architectural heuristics to shape representation evolution, limiting their ability to model data governed by intri
arXiv:2605.30467v1 Announce Type: new Abstract: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM) by combining diversity-aware regional-scale image curation with mask
arXiv:2605.30668v1 Announce Type: cross Abstract: Dialogue topic segmentation is critical in many human-AI collaborative applications which requires identifying heterogeneous boundary cues, including
arXiv:2605.30394v1 Announce Type: cross Abstract: This paper introduces Code Bench, a benchmark capable of evaluating Large Language Models (LLMs) concise code generation abilities in 60 programming l
arXiv:2605.31591v1 Announce Type: new Abstract: Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clini
arXiv:2605.30641v1 Announce Type: cross Abstract: Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought),
arXiv:2605.30981v1 Announce Type: new Abstract: Autoregressive language models frequently degrade during long-horizon generation, producing repetitive text, losing instruction adherence, and exhibitin
arXiv:2605.31264v1 Announce Type: new Abstract: LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and in
arXiv:2605.31058v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Langu
arXiv:2605.30842v1 Announce Type: new Abstract: Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this p
arXiv:2605.30488v1 Announce Type: new Abstract: Collaborative dense SLAM is essential for multi-robot teams to achieve scalable and consistent 3D perception across large-scale outdoor environments. Ex
arXiv:2605.31224v1 Announce Type: cross Abstract: The use of Generative AI Conversational User Interfaces (CUI) as a new way to access and analyze data is growing in all sectors, and the industrial on
arXiv:2605.30838v1 Announce Type: new Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmf
arXiv:2512.11779v2 Announce Type: replace-cross Abstract: Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although con
arXiv:2605.30487v1 Announce Type: new Abstract: Aligning large language models (LLMs) to heterogeneous and rapidly evolving safety requirements remains a critical challenge. Existing instruction-tuned
arXiv:2507.17026v2 Announce Type: replace-cross Abstract: The two-sample testing problem, a fundamental task in statistics and machine learning, seeks to determine whether two sets of samples, drawn f
arXiv:2605.30807v1 Announce Type: new Abstract: Conditional generative models have recently achieved remarkable success in various applications. However, a suitable metric for evaluating the reliabili
arXiv:2601.06453v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However,
arXiv:2605.31073v1 Announce Type: new Abstract: Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do
arXiv:2605.31494v1 Announce Type: new Abstract: Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by
arXiv:2605.30610v1 Announce Type: new Abstract: Adapting generative foundation models, in particular diffusion and flow models, to optimize given reward functions (e.g., binding affinity) while satisf
arXiv:2605.31388v1 Announce Type: new Abstract: Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While
arXiv:2601.01754v3 Announce Type: replace-cross Abstract: Transformers excel empirically on tasks that process well-formed inputs according to some grammar, such as natural language and code. However,
arXiv:2605.31291v1 Announce Type: cross Abstract: Recommender systems may operate under multiple, competing objectives. For example, audience reach, cultural values, public service mandate, and operat
arXiv:2605.30689v1 Announce Type: cross Abstract: Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches
arXiv:2605.30631v1 Announce Type: cross Abstract: While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains
arXiv:2605.30648v1 Announce Type: new Abstract: Recent work has analyzed the convergence of first-order methods under non-uniform smoothness assumptions that better model the loss landscape in machine
arXiv:2605.31172v1 Announce Type: new Abstract: This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in
arXiv:2605.31239v1 Announce Type: cross Abstract: Bagging-based ensembles, most notably Adaptive Random Forests, are among the strongest performers for learning from data streams. A common denominator
arXiv:2507.12453v5 Announce Type: replace Abstract: In automated machine learning, scientific discovery, and other applications of Bayesian optimization, deciding when to stop evaluating expensive bla
arXiv:2605.30846v1 Announce Type: new Abstract: Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing c
arXiv:2605.30590v1 Announce Type: cross Abstract: Two clinical AI systems can score nearly identically on coverage-based rubrics yet behave radically differently when their patient inputs change: one
arXiv:2605.30653v1 Announce Type: new Abstract: Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable.
arXiv:2605.11946v2 Announce Type: replace Abstract: Large Language Model agents are increasingly augmented with agent skills. Current evaluation methods for skills remain limited. Most deployed benchm
arXiv:2605.30611v1 Announce Type: cross Abstract: Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains
arXiv:2512.11571v2 Announce Type: replace Abstract: Autonomously performing tasks often requires robots to plan high-level discrete actions and continuous low-level motions to realize them. Previous T
arXiv:2605.30836v1 Announce Type: new Abstract: Recent SVD based compression methods for large language models like SVD LLM and Basis Sharing can be unified under one optimization problem. While mathe
arXiv:2605.30443v1 Announce Type: new Abstract: Multilingual large language models can generate figurative language, but whether the internal signals driving this behavior are language-specific or reu
arXiv:2501.01926v3 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still s
arXiv:2605.31093v1 Announce Type: new Abstract: Breast cancer is a major global health concern, and mammography screening plays a central role in early detection. The large volume of screening examina
arXiv:2605.30640v1 Announce Type: cross Abstract: Low-rank adaptation has become a standard method for parameter-efficient fine-tuning of large language models, but even small amounts of unsafe or adv