Knowledge catalogue
arXiv:2608.08910v1 Announce Type: new Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales. Tying the scales to a fixed ratio of three collapses
arXiv:2608.08512v1 Announce Type: new Abstract: Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time, so a question has diff
arXiv:2608.09091v1 Announce Type: cross Abstract: Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon m
arXiv:2604.00715v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensi
arXiv:2511.15709v2 Announce Type: replace Abstract: Recent works have shown that tokenisation is NP-complete. However, these works assume tokenisation is applied to inputs with unboundedly large alpha
arXiv:2608.07713v1 Announce Type: new Abstract: Latent medical image generators usually treat the tokenizer as fixed preprocessing. We test whether this separation is valid in a controlled ChestMNIST
arXiv:2608.08139v1 Announce Type: new Abstract: Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challen
arXiv:2608.08727v1 Announce Type: cross Abstract: To address this gap, we introduce TomaMMU, a large-scale Tomato leaf disease MultiModal Understanding dataset, alongside TomaBench, a benchmark for ev
arXiv:2608.07917v1 Announce Type: new Abstract: Chinese historical documents preserve valuable cultural heritage, but many collections remain accessible only as scanned page images, preventing full-te
arXiv:2608.08048v1 Announce Type: cross Abstract: This paper presents, for the first time in power systems literature to our knowledge, analytical tools to explain the training performance of machine
arXiv:2509.23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because
arXiv:2608.08907v1 Announce Type: cross Abstract: Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then
arXiv:2509.24039v2 Announce Type: replace-cross Abstract: If topography is a fundamental feature of the brain, it should influence both how neurons are arranged in space (i.e. explain brain maps) and
arXiv:2608.08951v1 Announce Type: new Abstract: Palm-vein recognition is a fine-grained biometric task in which both local vascular texture and the global layout of the vessel tree carry discriminativ
arXiv:2608.08919v1 Announce Type: cross Abstract: During standard radiotherapy planning, repeated CT acquisitions are often required for patient registration, verification, and adaptive planning, resu
arXiv:2608.08844v1 Announce Type: new Abstract: Surgical instrument segmentation is a fundamental task for computer-assisted interventions, yet most existing methods rely on pixel-level annotations or
arXiv:2608.08795v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external o
arXiv:2608.08508v1 Announce Type: new Abstract: This paper presents doctoral research on adaptive video super-resolution and perceptual quality modeling under real-world conditions. Existing video sup
arXiv:2608.07473v1 Announce Type: new Abstract: Evaluative AI (EAI) has been recently proposed as a way to support human decision-making, not by producing a single recommendation, but by presenting co
arXiv:2608.08885v1 Announce Type: cross Abstract: Reggaeton is one of the most widely consumed music genres in the world, and its lyrics are commonly regarded as highly sexualized. This claim rests mo
arXiv:2608.09541v1 Announce Type: new Abstract: Connected Autonomous Vehicles (CAVs) increasingly exploit Vehicle-to-Everything (V2X) communication to exchange multi-source sensor information, enablin
arXiv:2608.09861v1 Announce Type: new Abstract: Audio-visual interaction is the standard for patient-physician consultations, enabling natural communication and effective assessment of illness through
arXiv:2608.09529v1 Announce Type: new Abstract: As an important subfield of cross-modal generation, synthesizing static visual content in the form of images from audio, namely audio-to-image (A2I) gen
arXiv:2511.18721v4 Announce Type: replace-cross Abstract: The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict 'k-unstable' assumption that
arXiv:2608.07700v1 Announce Type: new Abstract: Translating a natural-language question into a SPARQL query that can be executed against a large knowledge graph requires resolving lexical ambiguity, g
arXiv:2608.08446v1 Announce Type: new Abstract: Personalized generation systems retrieve user history by request--memory relevance and inject it into the model context. Yet relevant history may concer
arXiv:2608.09153v1 Announce Type: new Abstract: Production AI agents fail when their context sources -- system prompts, knowledge bases, tool descriptions, and procedural skills -- contain errors or g
arXiv:2608.07630v1 Announce Type: new Abstract: We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty
arXiv:2608.09501v1 Announce Type: new Abstract: We consider the extensive-form bandit problem where on each trial the learner plays an extensive-form game against an oblivious adversary. We focus on t
arXiv:2608.09558v1 Announce Type: new Abstract: How expressive is prompting a transformer? Answering this question is important for separating the roles of prompting, architecture, and pretraining in
arXiv:2608.07524v1 Announce Type: new Abstract: Training deep learning models on variable long sequences poses significant computational challenges. Existing methods force a difficult trade-off betwee
arXiv:2608.08631v1 Announce Type: new Abstract: Digital-twin calibration requires interaction data that is expensive to collect. We study two acquisition decisions: which trajectories to generate, and
arXiv:2608.09125v1 Announce Type: new Abstract: Surgical robotic systems are increasingly being adopted as clinical workload rises, motivating autonomous solutions for repetitive manipulation subtasks
arXiv:2608.09464v1 Announce Type: cross Abstract: This paper studies hidden-target localization from range-bearing packets reported by a relay beacon whose global position and yaw are unknown. The veh
arXiv:2608.08554v1 Announce Type: cross Abstract: Power amplifier (PA) nonlinearity and memory effects significantly limit the spectral compliance, reliability, and energy efficiency of communication
arXiv:2505.15662v3 Announce Type: replace-cross Abstract: We introduce Transformer-based Neural Quantum Digital Twins (Tx-NQDTs) to reconstruct the low-energy spectral evolution of many-body quantum s
arXiv:2506.19125v2 Announce Type: replace-cross Abstract: Although transformers are most commonly optimized as statistical sequence models, it is unclear to what extent they can implement and learn ex
arXiv:2408.04619v2 Announce Type: replace-cross Abstract: The Transformer architecture underpins modern large language models powering state-of-the-art text generation and AI applications. However, it
arXiv:2512.08462v2 Announce Type: replace Abstract: Decoding brain states from functional magnetic resonance imaging (fMRI) data is vital for advancing neuroscience and clinical applications. While tr
arXiv:2608.01924v2 Announce Type: replace-cross Abstract: Personalized neoantigen prediction is challenging due to the scarcity of positive samples, the noise of the experimental data, the severe clas
arXiv:2608.07540v1 Announce Type: new Abstract: AI systems increasingly operate between flexible input representations and formal objects used by downstream tools. A key challenge is recognizing when
arXiv:2608.09044v1 Announce Type: new Abstract: Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically r
arXiv:2504.20114v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require
arXiv:2608.09052v1 Announce Type: cross Abstract: Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA. H
arXiv:2608.09522v1 Announce Type: new Abstract: Automated detection of subsurface cavities from Ground Penetrating Radar (GPR) is most difficult in soft, high-water-content ground, where conductive, w
arXiv:2608.08354v1 Announce Type: new Abstract: Tropical cyclones are growing more destructive in a changing climate, and efficient forecasting of their structure and track has become a necessity. Dee
arXiv:2608.08491v1 Announce Type: new Abstract: Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond han
arXiv:2507.00945v2 Announce Type: replace Abstract: Short-term forecasting of aggregated human mobility flows supports urban planning, intelligent transportation systems, and emergency response, yet e
arXiv:2608.08119v1 Announce Type: new Abstract: The rapid advancement of artificial intelligence (AI) has significantly accelerated research in time-series analysis, particularly in forecasting, class
arXiv:2608.09605v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as powerful tools for improving recommendation systems. The effectiveness of LLMs arises from their ability
arXiv:2608.08982v1 Announce Type: new Abstract: Interactive video world models generate rollouts autoregressively under an action stream, yet they are trained and evaluated almost exclusively on factu
arXiv:2606.12691v2 Announce Type: replace-cross Abstract: Auto-regressive models have emerged as powerful tools for sequential data, from language to video. Understanding how and why these models lear
arXiv:2608.09071v1 Announce Type: cross Abstract: Forward uncertainty propagation in complex physical systems can induce structured covariance across field-valued outputs. For a probabilistic surrogat
arXiv:2608.09198v1 Announce Type: new Abstract: Conventional robotic grippers often use high-ratio transmissions to generate grasping torque and external force sensors to measure physical interaction.
arXiv:2608.07534v1 Announce Type: cross Abstract: Ultraconstructive Model Theory (UCMT) replaces idealized satisfaction, at finite compu- tational scale, by bounded adversarial survival. A finite part
arXiv:2608.08601v1 Announce Type: new Abstract: To anticipate socio-technical risks from AI agents, organizations need taxonomies to classify them. However, existing AI risk taxonomies focus on broad
arXiv:2602.06343v3 Announce Type: replace Abstract: High-fidelity rendering of dynamic humans from monocular videos typically degrades catastrophically under occlusions. Existing solutions incorporate
arXiv:2604.00997v2 Announce Type: replace Abstract: Reward factorization personalizes large language models (LLMs) by decomposing rewards into shared basis functions and user-specific weights. Yet, ex
arXiv:1312.0925v4 Announce Type: replace Abstract: Alternating Minimization is a widely used and empirically successful heuristic for matrix completion and related low-rank optimization problems. Theo
arXiv:2608.08506v1 Announce Type: new Abstract: Training-free low-rank compression frameworks have been gaining prominence for LLM compression given their effectiveness in reducing model parameter cou