Knowledge catalogue
arXiv:2506.18141v3 Announce Type: replace Abstract: We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (S
arXiv:2604.17350v1 Announce Type: cross Abstract: Time series forecasting is traditionally dominated by sequence-based architectures such as recurrent neural networks and attention mechanisms, which p
arXiv:2604.17397v1 Announce Type: new Abstract: Autoregressive video diffusion is emerging as a promising paradigm for streaming video synthesis, with step distillation serving as the primary means of
arXiv:2509.24328v2 Announce Type: replace Abstract: LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to
arXiv:2604.18284v1 Announce Type: new Abstract: Pre-trained vision models have found widespread application across diverse domains. Prompt tuning-based methods have emerged as a parameter-efficient pa
arXiv:2601.07155v2 Announce Type: replace Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however,
arXiv:2604.17887v1 Announce Type: new Abstract: Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy executio
arXiv:2510.02025v4 Announce Type: replace Abstract: We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers
arXiv:2604.17782v1 Announce Type: new Abstract: Zero-shot EEG-to-image retrieval aims to decode perceived visual content from electroencephalography (EEG) by aligning neural responses with pretrained
arXiv:2604.18210v1 Announce Type: cross Abstract: Success in association football relies on both individual skill and coordinated tactics. While recent advancements in spatio-temporal data and deep le
arXiv:2603.02972v2 Announce Type: replace Abstract: Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch: V
arXiv:2508.11184v2 Announce Type: replace Abstract: Distractors-incorrect yet plausible answer choices in multiple-choice questions (MCQs)-are vital in educational assessments, as they help identify s
arXiv:2601.04695v2 Announce Type: replace-cross Abstract: Out-of-distribution generalization in reinforcement learning is hard to diagnose when benchmark shifts mix dynamics, observations, goals, and
arXiv:2604.17566v1 Announce Type: cross Abstract: Machine learning is becoming increasingly important for nonlinear system identification, including dynamical systems with spatially distributed output
arXiv:2604.16926v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet
arXiv:2412.08812v2 Announce Type: replace Abstract: Reward models trained on aggregate preferences often fail to capture individual users' values, but existing adaptation methods such as fine-tuning o
arXiv:2510.07761v2 Announce Type: replace Abstract: Large language models (LLMs) now give reasoning before answering, excelling in tasks like multiple-choice question answering (MCQA). Yet, a concern
arXiv:2509.07024v2 Announce Type: replace-cross Abstract: The Trapped Gyro-Landau Fluid (TGLF) model provides fast, accurate predictions of turbulent transport in tokamaks, but whole device simulation
arXiv:2601.00514v2 Announce Type: replace-cross Abstract: Do reasoning models have 'Aha!' moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead
arXiv:2509.02547v5 Announce Type: replace-cross Abstract: The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large
arXiv:2506.09885v2 Announce Type: replace Abstract: Recent advances in feed-forward Novel View Synthesis (NVS) have led to a divergence between two design philosophies: bias-driven methods, which rely
arXiv:2604.18352v1 Announce Type: cross Abstract: State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarant
arXiv:2508.17434v2 Announce Type: replace Abstract: Real-world image super-resolution (Real-ISR) focuses on recovering high-quality images from low-resolution inputs that suffer from complex degradati
arXiv:2604.17384v1 Announce Type: new Abstract: Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved sa
arXiv:2604.18089v1 Announce Type: new Abstract: Bayesian Deep Ensembles (BDEs) represent a powerful approach for uncertainty quantification in deep learning, combining the robustness of Deep Ensembles
arXiv:2604.17674v1 Announce Type: new Abstract: Legal practitioners and judicial institutions face an ever-growing volume of case-law documents characterised by formalised language, lengthy sentence s
arXiv:2604.18067v1 Announce Type: new Abstract: The miniaturisation of neural processing units (NPUs) and other low-power accelerators has enabled their integration into microcontroller-scale wearable
arXiv:2604.18208v1 Announce Type: new Abstract: Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities that impede the training of deep learning networks f
arXiv:2512.07407v2 Announce Type: replace Abstract: Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use P
arXiv:2604.16748v1 Announce Type: new Abstract: Time series forecasting plays a pivotal role in critical sectors such as finance, energy, transportation, and meteorology. However, Long-term Time Serie
arXiv:2603.19684v2 Announce Type: replace Abstract: Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing a
arXiv:2512.20249v3 Announce Type: replace-cross Abstract: Multimodal brain decoding aims to reconstruct semantic information that is consistent with visual stimuli from brain activity signals such as
arXiv:2604.16914v1 Announce Type: new Abstract: Clinical ultrasound analysis demands models that generalize across heterogeneous organs, views, and devices, while supporting interpretable workflow-lev
arXiv:2506.00065v2 Announce Type: replace Abstract: Multimodal language models (MLMs) increasingly demonstrate human-like communication, yet their use of everyday perspectival words remains poorly und
arXiv:2509.16538v3 Announce Type: replace-cross Abstract: We propose VC-Inspector, a lightweight, open-source large multimodal model (LMM) for reference-free evaluation of video captions, with a focus
arXiv:2604.17656v1 Announce Type: cross Abstract: Video-to-music (V2M) is the fundamental task of creating background music for an input video. Recent V2M models achieve audiovisual alignment by typic
arXiv:2604.17801v1 Announce Type: new Abstract: Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view
arXiv:2508.15229v3 Announce Type: replace Abstract: Small Language Models (SLMs) provide computational advantages in resource-constrained environments, yet memory limitations remain a critical bottlen
arXiv:2508.16464v2 Announce Type: replace Abstract: Entities in discourse vary in salience: main participants, objects and locations stay prominent, while others are quickly forgotten, raising questio
arXiv:2601.04043v2 Announce Type: replace Abstract: As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to
arXiv:2604.17040v1 Announce Type: new Abstract: Spiking neural operators are appealing for neuromorphic edge computing because event-driven substrates can, in principle, translate sparse activity into
arXiv:2603.22368v2 Announce Type: replace Abstract: Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. Whi
arXiv:2604.16855v1 Announce Type: new Abstract: Camouflaged object detection (COD) segments objects that intentionally blend with the background, so predictions depend on subtle texture and boundary c
arXiv:2604.17031v1 Announce Type: new Abstract: The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds. We approach this pr
arXiv:2604.15453v1 Announce Type: cross Abstract: Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, token
arXiv:2604.15617v1 Announce Type: cross Abstract: Hyperbolic conservation laws govern a wide range of transport-driven dynamics featuring shocks, contact discontinuities, and complex wave interactions
arXiv:2604.15789v1 Announce Type: new Abstract: As Large Language Models (LLMs) receive increasing attention and are being deployed across various domains, their potential risks, including generating
arXiv:2604.16234v1 Announce Type: cross Abstract: Academic integrity continues to face the persistent challenge of examination cheating. Traditional invigilation relies on human observation, which is
arXiv:2604.15622v1 Announce Type: new Abstract: Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices
arXiv:2604.15809v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grou
This post references @dexhorthy quoting the Z/L continuum concept at an AIE Miami event, suggesting the idea is gaining traction in AI discussions. The Z/L continuum appears to be a framework or model
arXiv:2604.15708v1 Announce Type: new Abstract: The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Alth
arXiv:2603.24621v2 Announce Type: replace Abstract: We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents
arXiv:2601.07160v2 Announce Type: replace Abstract: To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. Ho
arXiv:2509.01944v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimoda
arXiv:2604.15359v1 Announce Type: cross Abstract: Understanding communication behavior in modern system-on-chip (SoC) designs is critical for functional verification, performance analysis, and post-si
Release b8855 addresses a crash in llama-tokenize when using the vocab_only flag with GLM-DSA models and fixes a crash in print_info for GLM-DSA when vocab_only is set. This is a bugfix release for th
arXiv:2604.16241v1 Announce Type: cross Abstract: Large language models have shown strong performance on broad-domain knowledge and reasoning benchmarks, but it remains unclear how well language model
arXiv:2604.15503v1 Announce Type: new Abstract: Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language
arXiv:2505.21569v3 Announce Type: replace-cross Abstract: Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance