Knowledge catalogue
arXiv:2610.16084v1 Announce Type: new Abstract: Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for b
arXiv:2610.14115v1 Announce Type: new Abstract: Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents tha
arXiv:2610.18445v1 Announce Type: new Abstract: Automating AI research creates a positive feedback loop between software capability and research effort. We study a stochastic realisation of this loop
arXiv:2610.18511v1 Announce Type: new Abstract: Buildings cause nearly 40% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60% and account
arXiv:2610.19387v1 Announce Type: new Abstract: Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scor
arXiv:2610.19074v1 Announce Type: new Abstract: Reliable uncertainty quantification remains an important challenge in AI. Hierarchical Bayesian methods provide a principled framework for this by repre
arXiv:2610.14736v1 Announce Type: new Abstract: Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate solutions through natural-language prompting. How
arXiv:2610.17324v1 Announce Type: cross Abstract: AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does
arXiv:2606.14715v2 Announce Type: replace-cross Abstract: LLM agents are increasingly used to simulate real-world interactions, but it remains unclear whether simulated behaviors preserve the content
arXiv:2610.20476v1 Announce Type: new Abstract: Real-time volumetric mapping for a planning robot is dominated by the cost of integrating and storing information at the finest resolution, yet only a s
arXiv:2610.19725v1 Announce Type: new Abstract: Time-series foundation models provide strong zero-shot forecast, but deployment for real- world applications still requires task-specific designs for mo
arXiv:2610.19210v1 Announce Type: new Abstract: Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference re
arXiv:2610.19934v1 Announce Type: new Abstract: Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much
arXiv:2610.18883v1 Announce Type: new Abstract: Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-stud
arXiv:2610.14984v1 Announce Type: cross Abstract: Generative AI makes options cheap and shifts the bottleneck of creative work from generating options to screening them. We argue that AI's value depen
arXiv:2610.19323v1 Announce Type: new Abstract: Recent advancements in topic modeling have split into two main paths: efficient embedding-based methods that offer scalability but are often outperforme
arXiv:2610.19403v1 Announce Type: new Abstract: Discrete multi-group pipe routers place channels on a grid or coarse graph. The resulting centerlines are topologically feasible but typically contain m
arXiv:2610.18924v1 Announce Type: cross Abstract: Interpreting electron paramagnetic resonance (EPR) spectra commonly requires repeated forward simulation and optimization of spin Hamiltonian paramete
arXiv:2507.21137v2 Announce Type: replace Abstract: In this paper we try to answer the question 'What constitutes Sudoku difficulty rating across different Sudoku websites?' Using two distinct methods
arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowled
arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextu
arXiv:2610.16127v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored in the Architecture, Engineering, and Construction (AEC) domain, yet their reliability in regul
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitat
arXiv:2610.20442v1 Announce Type: new Abstract: Foundation models are driving a paradigm shift in robotic intelligence, moving beyond low-level action prediction to goal-directed orchestration of data
arXiv:2610.20490v1 Announce Type: new Abstract: Certifiable optimization provides global optimality guarantees for non-convex state estimation in robotics. However, under severe physical sensing degen
arXiv:2610.19492v1 Announce Type: new Abstract: Streaming Inverse Text Normalization (ITN) is vital for converting spoken-form outputs from streaming Automatic Speech Recognition into formatted writte
arXiv:2610.14701v1 Announce Type: cross Abstract: Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training. While
arXiv:2610.17296v1 Announce Type: new Abstract: Emerging healthcare services, such as real-time diagnostics, remote health monitoring and computer-assisted surgery, require stringent Quality of Servic
arXiv:2610.19142v1 Announce Type: new Abstract: Graph Neural Networks on large graphs commonly rely on in-memory graph storage with ad hoc data processing pipelines for both training and inference. Gr
arXiv:2610.15055v1 Announce Type: new Abstract: Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before. That difference can credit a frozen res
arXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose
arXiv:2610.19133v1 Announce Type: new Abstract: Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that defense
arXiv:2610.19041v1 Announce Type: cross Abstract: Understanding the dynamics of language acquisition in Large Language Models (LLMs) is crucial for uncovering how statistical representations evolve in
arXiv:2610.20416v1 Announce Type: new Abstract: For the fundamental problem of prediction from expert advice, Freund asked whether one could compete with a comparator that switches k times among only
arXiv:2512.10309v3 Announce Type: replace-cross Abstract: Chemical reaction networks are widely used to model stochastic dynamics in biophysical processes. Their exact probabilistic description via th
arXiv:2610.19401v1 Announce Type: cross Abstract: As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to b
arXiv:2610.20069v1 Announce Type: new Abstract: What makes a deep network train, and what shape is its loss surface? We answer both with one construction at two scales: a polynomial activation f (z) =
arXiv:2610.14776v1 Announce Type: cross Abstract: Text-to-speech (TTS) systems are conventionally optimized for intelligibility and speaker similarity. However, neither objective captures the prosodic
arXiv:2610.20337v1 Announce Type: new Abstract: The success of transformers is attributed to several factors, including their capacity to express formal languages over variable-length inputs, and abil
arXiv:2610.20401v1 Announce Type: new Abstract: Reinforcement learning makes language models better at solving tasks, but the same mechanism also rewards guessing. When success is the only way to earn
arXiv:2511.00198v2 Announce Type: replace-cross Abstract: Autoregressive language models are usually trained with next-token prediction under a fixed left-to-right target order. This paper studies tar
arXiv:2610.16887v1 Announce Type: new Abstract: Transparency in AI-supported decision systems is widely required but poorly defined. Existing approaches treat transparency as a property of systems or
arXiv:2610.16916v1 Announce Type: new Abstract: The European Union's Artificial Intelligence Act introduces a structured framework for governing high-risk AI systems, emphasizing transparency, risk ma
arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly assoc
arXiv:2610.19067v1 Announce Type: new Abstract: A wearable assistive robot must continuously estimate terrain, locomotion mode, gait phase, and walking speed. These quantities are commonly addressed b
arXiv:2601.12355v3 Announce Type: replace Abstract: To lower the expertise barrier in machine learning, the AutoML community has focused on the CASH problem, which jointly automates algorithm selectio
arXiv:2610.20334v1 Announce Type: cross Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path
arXiv:2610.20175v1 Announce Type: new Abstract: Parallel drafters such as DFlash and DSpark reduce proposal latency, but early mismatches limit how much of each block can be accepted. Retaining altern
arXiv:2610.15136v1 Announce Type: new Abstract: Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthiness
arXiv:2504.07170v3 Announce Type: replace Abstract: Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainabil
arXiv:2610.19316v1 Announce Type: cross Abstract: Assigning routine tasks to cheaper large language model (LLM) providers can reduce generation cost, but switching providers may require processing acc
arXiv:2610.19608v1 Announce Type: cross Abstract: Counts of which brands a large language model names are useful only if they hold long enough to act on. We test this with a pre-registered replication
arXiv:2610.18617v1 Announce Type: new Abstract: An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of inf
arXiv:2610.19539v1 Announce Type: new Abstract: Aggregate performance metrics do not identify local modelling inaccuracies in machine learning (ML) surrogates used for thermal-system optimisation. Thi
arXiv:2610.19536v1 Announce Type: new Abstract: Typed decision models are language models that answer a question with a fixed set of possible answers by returning a probability for each answer instead
arXiv:2610.16942v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are fast becoming a general interface to sound, yet how far their broad pretraining carries into specialized domai
arXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally r
arXiv:2610.15028v1 Announce Type: cross Abstract: Recent bidirectional encoders have been modernized with innovations from causal large language models (LLMs). However, the pretraining recipe itself r
arXiv:2610.19714v1 Announce Type: new Abstract: Learning robust driving policies that generalize beyond their training domain remains a central challenge in motion planning. We propose an uncertainty-
arXiv:2502.12713v2 Announce Type: replace Abstract: Echocardiography plays a fundamental role in the extraction of clinical parameters (e.g. left ventricular volume and ejection fraction) required to