arXiv:2512.20573v3 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a strength for drafters in speculative decoding with autoregressive (AR) verifiers. Our core insight is that […]
Diffusion Timbre Transfer Via Mutual Information Guided Inpainting
arXiv:2601.01294v2 Announce Type: replace-cross Abstract: We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise injection that targets latent channels most informative of instrument identity, and (ii) an early-step clamping mechanism […]
Robust Distributed Learning under Resource Constraints: Decentralized Quantile Estimation via (Asynchronous) ADMM
arXiv:2601.20571v1 Announce Type: cross Abstract: Specifications for decentralized learning on resource-constrained edge devices require algorithms that are communication-efficient, robust to data corruption, and lightweight in memory usage. While state-of-the-art gossip-based methods satisfy the first requirement, achieving robustness remains challenging. Asynchronous decentralized ADMM-based methods have been explored for estimating the median, a statistical centrality measure that […]
Independence of Approximate Clones
arXiv:2601.20779v1 Announce Type: cross Abstract: In an ordinal election, two candidates are said to be perfect clones if every voter ranks them adjacently. The independence of clones axiom then states that removing one of the two clones should not change the election outcome. This axiom has been extensively studied in social choice theory, and several […]
ShareChat: A Dataset of Chatbot Conversations in the Wild
arXiv:2512.17843v3 Announce Type: replace-cross Abstract: While academic research typically treats Large Language Models (LLM) as generic text generators, they are distinct commercial products with unique interfaces and capabilities that fundamentally shape user behavior. Current datasets obscure this reality by collecting text-only data through uniform interfaces that fail to capture authentic chatbot usage. To address this […]
DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problems
arXiv:2506.06052v3 Announce Type: replace Abstract: Discrete Combinatorial Problems (DCPs) are prevalent in industrial decision-making and optimisation. However, while constraint solving technologies for DCPs have advanced significantly, the core process of formalising them, namely constraint modelling, requires significant expertise and remains a bottleneck for wider adoption. Aiming to alleviate this bottleneck, recent studies have explored using […]
ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching
arXiv:2509.15942v2 Announce Type: replace-cross Abstract: Climate projections have uncertainties related to components of the climate system and their interactions. A typical approach to quantifying these uncertainties is to use climate models to create ensembles of repeated simulations under different initial conditions. Due to the complexity of these simulations, generating such ensembles of projections is computationally […]
CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
arXiv:2512.23880v2 Announce Type: replace Abstract: Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability to complex scientific tasks. We introduce CASCADE, a self-evolving agentic framework representing an early instantiation of the transition from “LLM + tool use” to “LLM + skill acquisition”. CASCADE enables agents […]
Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization
arXiv:2510.23530v2 Announce Type: replace-cross Abstract: Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a high-compression Consistency Autoencoder (CAE) by using data augmentation, thereby inducing homogeneity (equivariance to scalar gain) and additivity (the […]
Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
arXiv:2501.19180v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial training, often fail to cover corner cases or rare domains, leaving LLMs still vulnerable to more […]
LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP
arXiv:2408.04628v2 Announce Type: replace-cross Abstract: Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens. However, creating an analogous representation for ancient logographic writing systems is an extremely labor intensive process that requires expert knowledge. At present, a large portion of logographic data persists in […]
Orca: Browsing at Scale Through User-Driven and AI-Facilitated Orchestration Across Malleable Webpages
arXiv:2505.22831v2 Announce Type: replace-cross Abstract: Web-based activities span multiple webpages. However, conventional browsers with stacks of tabs cannot support operating and synthesizing large volumes of information across pages. While recent AI systems enable fully automated web browsing and information synthesis, they often diminish user agency and hinder contextual understanding. We explore how AI could instead […]