Knowledge catalogue
arXiv:2609.26112v1 Announce Type: new Abstract: Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded inp
arXiv:2609.25058v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) adapts large language models (LLMs) to downstream tasks while updating only a small fraction of their pretrained
arXiv:2609.25948v1 Announce Type: cross Abstract: Target-speaker and multi-speaker extraction are techniques for extracting speech from a desired speaker or desired speakers in the presence of other s
arXiv:2511.17909v2 Announce Type: replace Abstract: Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often rel
arXiv:2609.26306v1 Announce Type: new Abstract: This work presents the task and results of the CHiME-9 challenge for Enhancing Conversations to address Hearing Impairment. The challenge considers the
arXiv:2511.15371v3 Announce Type: replace Abstract: Assessing the importance of individual features in Machine Learning is critical to understand the model's decision-making process. While numerous me
arXiv:2604.07733v2 Announce Type: replace Abstract: Evaluating strategic decision-making in LLM-based agents requires generative, competitive, and longitudinal environments, yet few benchmarks provide
arXiv:2609.26779v1 Announce Type: cross Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context
arXiv:2609.25939v1 Announce Type: new Abstract: The performance of large language model (LLM) workflows often depends on selecting a small set of in-context demonstrations to guide model behavior on n
arXiv:2609.25654v1 Announce Type: cross Abstract: Robots operating safely in cluttered everyday environments often need to infer scene geometry from partial observations. Methods that detect objects i
arXiv:2609.26458v1 Announce Type: new Abstract: We introduce extbf{CoDeR}, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual
arXiv:2609.26094v1 Announce Type: new Abstract: Multi-step causal reasoning requires chaining inferences where each step constrains the next. An early error propagates silently, and a correct answer r
arXiv:2609.25453v1 Announce Type: new Abstract: Medical image analysis remains fundamentally challenging because of the intricate geometric and topological structures present in medical data. Conventi
arXiv:2609.26399v1 Announce Type: new Abstract: Scene safety understanding plays a life-or-death role in situational awareness in various critical domains. Traditional methods that rely on learning di
arXiv:2608.28021v2 Announce Type: replace-cross Abstract: Large language models increasingly author Infrastructure-as-Code (IaC), where one insecure default is provisioned straight into production. Pr
arXiv:2609.26300v1 Announce Type: new Abstract: Despite their strong performance, large language models (LLMs) are bottlenecked by KV cache memory traffic during long-context inference. Sparse attenti
arXiv:2609.26463v1 Announce Type: new Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Ra
arXiv:2609.26173v1 Announce Type: new Abstract: Many post-training quantization (PTQ) methods use layer-wise reconstruction, second-order proxy objectives, or activation-aware transformations to reduc
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latenc
arXiv:2609.25340v1 Announce Type: new Abstract: Concept drift is a common phenomenon in real-world data streams, in which changes in the data-generating distribution can degrade predictive model perfo
arXiv:2603.16829v2 Announce Type: replace-cross Abstract: Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example,
arXiv:2609.25924v1 Announce Type: cross Abstract: Causal inference guides operational and managerial decisions but remains challenging in high-dimensional panel or tensor settings, where decisions may
arXiv:2609.25447v1 Announce Type: new Abstract: We study what LLMs do when a user applies pressure in an uncomfortable situation: a user insists, begs, flatters or grieves, and the model gives up a co
arXiv:2609.24456v1 Announce Type: cross Abstract: Distributed reinforcement learning (RL) scales training by parallelizing actors and learners around an Experience Buffer. As RL workloads grow, howeve
arXiv:2606.13591v2 Announce Type: replace-cross Abstract: Multiagent language model systems, such as collaborative reasoning and debate, produce multiple correlated candidate answers and confidence si
arXiv:2609.23894v1 Announce Type: cross Abstract: Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other age
arXiv:2609.24760v1 Announce Type: new Abstract: When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting
arXiv:2609.25642v1 Announce Type: new Abstract: Closed-loop evaluation of surgical robots requires tissue that deforms, can be grasped and lifted, and reproduces the anatomy in which the robot will op
arXiv:2609.24016v1 Announce Type: new Abstract: Commercial large language models are increasingly deployed across African fintech infrastructure for fraud detection and customer communication, yet no
arXiv:2609.25501v1 Announce Type: new Abstract: We present the first method for native, continuous gradient descent for machine learning models with p-adic parameters. Existing native optimizers are d
arXiv:2609.25905v1 Announce Type: new Abstract: This paper presents a modular control barrier function (CBF) framework for safe free-flying robotic spacecraft operations during tumbling target capture
arXiv:2312.06632v2 Announce Type: replace Abstract: Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substa
arXiv:2609.24784v1 Announce Type: new Abstract: AI governance increasingly requires providers and public authorities to reason about multiple AI instantiations, alternative versions, and deployment co
arXiv:2609.25297v1 Announce Type: new Abstract: Prioritized experience replay (PER) improves sample efficiency by replaying high-priority transitions, usually according to absolute temporal-difference
arXiv:2609.25264v1 Announce Type: new Abstract: Cosserat rod models for soft robots usually construct sectional stiffness by summing material properties over a common cross-section. This assumption be
arXiv:2609.26236v1 Announce Type: new Abstract: Video watermarking underpins copyright protection and provenance for generated media, yet almost every video is compressed by a codec before it is store
arXiv:2609.26086v1 Announce Type: new Abstract: An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop.
arXiv:2609.23142v1 Announce Type: new Abstract: Building gameplay features in a game engine requires more than code, as code that compiles and runs does not necessarily implement the requested gamepla
arXiv:2609.24174v1 Announce Type: new Abstract: Long-horizon language agents receive sparse terminal feedback, while intermediate rubrics provide structured but potentially misspecified assessments of
arXiv:2609.26056v1 Announce Type: new Abstract: Vision-Language Models (VLMs) offer promising capabilities for automated sports coaching but face a fundamental limitation: they implicitly compare agai
arXiv:2609.26241v1 Announce Type: new Abstract: Post-training quantization and pruning rely on a small calibration corpus. Whether specialized domains such as finance require domain-matched calibratio
arXiv:2609.24369v1 Announce Type: cross Abstract: Deception plays a central role in Intelligence operations, yet it remains difficult to analyse systematically without expert knowledge of reasoning pa
arXiv:2609.24801v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation throug
arXiv:2601.08450v2 Announce Type: replace-cross Abstract: Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order
arXiv:2609.25650v1 Announce Type: new Abstract: Accurately isolating disease-related features from confounding covariates (e.g., age, gender, site) and individual variations remains a fundamental chal
arXiv:2609.26502v1 Announce Type: cross Abstract: Deep generative models are widely reported to enable de novo crystal structure prediction (CSP), but their capability has not been measured consistent
arXiv:2609.25397v1 Announce Type: new Abstract: The one-dimensional bin packing problem (1D-BPP) is a classical NP-hard combinatorial optimization problem with applications ranging from logistics and
arXiv:2609.25017v1 Announce Type: new Abstract: Deepfakes, synthetic audiovisual content produced by deep generative models, have escalated into a critical threat across civilian and military domains,
arXiv:2609.26426v1 Announce Type: new Abstract: Finite Element Analysis (FEA) is widely used for transient mechanical simulations, but its high computational cost limits real-time and high-resolution
arXiv:2408.16403v2 Announce Type: replace Abstract: Classical particle methods based on propagation of chaos (PoC) have been developed for solving mean-field stochastic differential equations and thei
arXiv:2609.25542v1 Announce Type: new Abstract: Corporate default prediction is a core problem in financial risk management, yet traditional credit models rely heavily on financial statements that are
arXiv:2609.25881v1 Announce Type: new Abstract: Virtual try-on (VTON) requires precise pixel-level fidelity, yet mainstream Diffusion Transformers (DiTs) often suffer from texture degradation and stru
arXiv:2609.25666v1 Announce Type: new Abstract: We present and tackle two problems associated with deploying Foundation Models (FMs) on Embodied Agents performing navigation: 1) Training bias in FMs l
arXiv:2609.26130v1 Announce Type: new Abstract: Crack detection is a crucial process to ensure the safety and longevity of buildings and other infrastructure. In this paper, we developed a low-cost, a
arXiv:2609.25724v1 Announce Type: new Abstract: This paper present a spiral-cavity wheel for lunar regolith excavation and a sensor-light evaluation stack that jointly estimates fill ratio (vision), s
arXiv:2609.26338v1 Announce Type: new Abstract: Argument Mining (AM) transforms natural language into its underlying argument structures. This transformation is typically realized through a sequence o
arXiv:2609.26156v1 Announce Type: cross Abstract: HCI and HRI studies often require short, repeatable arousal manipulations that can run while participants continue interacting with a device or robot.
arXiv:2609.25942v1 Announce Type: new Abstract: Robots operating around pedestrians often reason over a finite set of predicted human futures. Repeated online updates can concentrate this limited pred
arXiv:2609.26687v1 Announce Type: new Abstract: Distinguishing GPT-assisted from independently authored student writing has become a critical challenge in academia. This paper evaluates the discrimina
arXiv:2609.26113v1 Announce Type: new Abstract: A state-of-the-art language model asked to interpret 'most of most students passed' typically answers 'most,' though composing two instances of 'most' y