Knowledge catalogue
arXiv:2608.22922v1 Announce Type: new Abstract: We present HelaBERT, a family of two BERT-based masked language models pre-trained from scratch on approximately 1 billion tokens of Sinhala text source
arXiv:2608.22310v1 Announce Type: new Abstract: Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite d
arXiv:2608.23264v1 Announce Type: new Abstract: Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably lead
arXiv:2608.21863v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Rein
arXiv:2512.21076v2 Announce Type: replace-cross Abstract: The growing availability of books and textual materials in digital learning environments necessitates reliable semantic organization to suppor
arXiv:2608.23356v1 Announce Type: cross Abstract: Accurate watch-time (WT) prediction is an important requirement for short-video recommendations. Yet WT distributions are near-zero-inflated, long-tai
arXiv:2608.22981v1 Announce Type: new Abstract: Knowledge graphs are often accompanied by ontological class hierarchies that encode valuable semantic information, yet many link prediction methods eith
arXiv:2608.22839v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for scientific decision support, yet reliable confidence estimation remains difficult in black-box
arXiv:2608.21446v1 Announce Type: cross Abstract: We study whether the loss design of High-Fidelity Generative Image Compression (HiFiC), a GAN-based neural codec originally built for natural photogra
arXiv:2507.21984v2 Announce Type: replace-cross Abstract: Networks of phase oscillators can serve as dense associative memories when they incorporate genuine many-body coupling beyond the classical Ku
arXiv:2608.21868v1 Announce Type: new Abstract: Depression assessment from multimodal clinical interviews requires integrating dispersed evidence from multiple symptoms into a coherent PHQ-8 profile.
arXiv:2608.21811v1 Announce Type: new Abstract: Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answer
arXiv:2608.21792v1 Announce Type: new Abstract: Document classification in regulated industries is constrained by data residency, limited cold-start labels, scarce review capacity, and costly model-go
arXiv:2509.23928v3 Announce Type: replace-cross Abstract: Speculative decoding has proven effective for accelerating inference in Large Language Models (LLMs), yet its extension to Vision-Language Mod
arXiv:2601.12423v2 Announce Type: replace Abstract: Stereo vision between images faces a range of challenges, including occlusions, motion, and camera distortions, across applications in autonomous dr
arXiv:2608.22192v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused.
arXiv:2608.23543v1 Announce Type: new Abstract: While AI assistance can improve human task performance in the short term, it may also undermine the development of skills in the longer term. We examine
arXiv:2608.21756v1 Announce Type: cross Abstract: Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned representa
arXiv:2606.22342v2 Announce Type: replace Abstract: How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts.
arXiv:2608.23142v1 Announce Type: new Abstract: Vision-based wheat phenotyping requires repeated measurements under deployment constraints, from growth-stage recognition to wheat-head counting and org
arXiv:2608.23286v1 Announce Type: cross Abstract: Federated learning on non-IID data seeks flat minima to generalize across clients, and existing methods borrow sharpness-aware minimization from centr
arXiv:2608.23566v1 Announce Type: cross Abstract: Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prom
arXiv:2608.23448v1 Announce Type: new Abstract: This paper presents new Cantonese ParGram resources and evaluates LLMs for knowledge-driven grammar engineering within a controlled experimental paradig
arXiv:2608.21786v1 Announce Type: new Abstract: General image fusion seeks to integrate complementary information from multiple source images, yet real-world applications often require a single system
arXiv:2608.22692v1 Announce Type: new Abstract: As an important operation of image composition, object placement aims to predict the plausible placement (location, scale) for the inserted foreground o
arXiv:2608.22582v1 Announce Type: cross Abstract: Large-scale population surveys are essential for generating robust social and scientific insights, yet they face significant challenges, including dec
arXiv:2608.22238v1 Announce Type: new Abstract: HyperbolicCD pioneered hyperbolic geometry for point cloud completion by replacing the Euclidean Chamfer distance with arcosh(1+alpha||x-y||^2), but the
arXiv:2608.22665v1 Announce Type: cross Abstract: We investigate the token mixer in vision backbones by revisiting clustering, one of the most classic approaches in machine learning. An effective toke
arXiv:2608.22980v1 Announce Type: cross Abstract: Dense vector retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an embedding
arXiv:2407.05389v2 Announce Type: replace-cross Abstract: Underwater image enhancement (UIE) has attracted much attention owing to its importance for underwater operation and marine engineering. Motiv
arXiv:2608.23432v1 Announce Type: new Abstract: Accurate organ-at-risk segmentation is essential for radiotherapy planning, but reviewing segmentations is time-consuming and subjective. We investigate
arXiv:2608.21972v1 Announce Type: new Abstract: The sampling process of Denoising Diffusion Probabilistic Models (DDPMs) can be accelerated by leveraging second-order information in the form of approx
arXiv:2608.22076v1 Announce Type: cross Abstract: Rising energy demand, fossil fuel depletion and climate change highlight the need for more efficient energy production and consumption. Offshore oil a
arXiv:2608.22244v1 Announce Type: cross Abstract: Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades s
arXiv:2608.23061v1 Announce Type: new Abstract: Background: Automating clinical guideline-based decision-making with large language models (LLMs) remains challenging because of reliability, hallucinat
arXiv:2608.21685v1 Announce Type: new Abstract: This article presents a novel 3D reconstruction and mapping of the interior of the International Space Station (ISS) using 3D Gaussian Splatting (3DGS).
arXiv:2606.17443v2 Announce Type: replace Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new ch
arXiv:2608.22817v1 Announce Type: new Abstract: Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (
arXiv:2608.23546v1 Announce Type: cross Abstract: In this paper, we introduce the Inertial Manifold Neural Operator (IMNO) for solving dissipative time-dependent partial differential equations (PDEs).
arXiv:2608.22067v1 Announce Type: cross Abstract: World-Action Models (WAMs) build robot control on video-generation backbones, which jointly predict dense future visual trajectories and robot actions
arXiv:2608.23471v1 Announce Type: cross Abstract: Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question:
arXiv:2608.22990v1 Announce Type: new Abstract: Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by conditioning robot actions on natural-languag
arXiv:2608.23330v1 Announce Type: new Abstract: Video understanding requires intelligent agents to transcend mere recognition of visual facts and comprehend the underlying intents behind human actions
arXiv:2608.23538v1 Announce Type: cross Abstract: Modern AI models such as tabular foundation models and gradient-boosted ensembles can outpredict classical methods, but provide little basis for reaso
arXiv:2608.22515v1 Announce Type: cross Abstract: Reliable early disruption prediction is critical for the safe operation and real-time control of tokamaks. However, machine learning based prediction
arXiv:2608.21389v1 Announce Type: cross Abstract: Generative AI enables customized misinformation at scale, yet defenses remain largely reactive. We present empirical findings from a human-subject stu
arXiv:2608.23518v1 Announce Type: new Abstract: Vision-Language Models (VLMs) achieve strong performance in visual reasoning tasks, but it remains unclear whether they understand visual relations, or
arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reasoni
arXiv:2602.06064v2 Announce Type: replace-cross Abstract: Scheduling precedence-constrained tasks under shared renewable resources is critical to modern computing platforms. It is often modeled as the
arXiv:2608.22651v1 Announce Type: new Abstract: Modern text-to-SQL systems have become increasingly elaborate, relying on schema-linking modules, retrieval-augmented prompting, candidate generation, a
arXiv:2608.23098v1 Announce Type: new Abstract: Classical Chinese poetry composition has long valued Tuiqiao, the iterative refinement of words, imagery, and prosody. However, many current AI poetry s
arXiv:2608.22212v1 Announce Type: cross Abstract: Causal discovery aims to understand the relationships between individual random variables. In many applications, such as brain imaging and climate mod
arXiv:2608.21601v1 Announce Type: new Abstract: Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference solutio
arXiv:2608.21488v1 Announce Type: cross Abstract: While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are exp
arXiv:2608.23393v1 Announce Type: cross Abstract: KellyBoost is a single multi-output XGBoost model whose softmax output is the portfolio: with y the vector of per-asset holding-period returns, the tr
arXiv:2608.22506v1 Announce Type: new Abstract: Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of eac
arXiv:2608.22618v1 Announce Type: new Abstract: Individual patient data (IPD) from clinical trials is the substrate for survival modeling, meta-analysis, and safety research, yet IPD is rarely release
arXiv:2608.22916v1 Announce Type: new Abstract: Vision-language models are known to encode spatial information in their hidden states, yet often fail to use it when answering. However, it remains uncl
arXiv:2608.22389v1 Announce Type: cross Abstract: Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This remov
arXiv:2608.22457v1 Announce Type: new Abstract: An inner hood panel must meet a deflection target, stay below a stress limit, and hit a mass target. Machine-learned surrogates have made the forward di