Knowledge catalogue
arXiv:2606.06464v1 Announce Type: new Abstract: A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the sim
arXiv:2606.05561v1 Announce Type: new Abstract: Speech-based mental health screening offers scalable depression detection, yet clinical deployment faces a significant barrier: users' privacy concerns
arXiv:2606.06031v1 Announce Type: new Abstract: Masked diffusion language models generate text by iteratively unmasking many tokens in parallel, but this speed comes with a correction problem: tokens
arXiv:2606.06361v1 Announce Type: new Abstract: Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws.
arXiv:2606.05896v1 Announce Type: new Abstract: Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent fram
arXiv:2506.10145v3 Announce Type: replace Abstract: End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into th
arXiv:2606.05576v1 Announce Type: new Abstract: Vision-language models (VLMs) excel on visual question answering and multimodal reasoning benchmarks. Yet their capability on ultra-resolution images -
arXiv:2606.05718v1 Announce Type: new Abstract: On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher. In m
arXiv:2606.05736v1 Announce Type: new Abstract: Video reasoning aims to understand complex temporal events and causal relationships within videos. Recently, Chain-of-Thought (CoT) has been introduced
arXiv:2606.05979v1 Announce Type: new Abstract: We propose world-language-action (WLA) models as a new class of embodied foundation models. WLA takes textual instructions, images, and robot states as
arXiv:2510.11194v3 Announce Type: replace Abstract: Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current met
arXiv:2606.04323v1 Announce Type: new Abstract: In this report, we present our solution for Track 2 of the CVPR 2026 VidLLMs Challenge. This track evaluates visual relational reasoning in videos, wher
arXiv:2606.04069v1 Announce Type: cross Abstract: Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations an
arXiv:2606.04165v1 Announce Type: cross Abstract: High-precision calorimeter simulation at current and future colliders imposes rapidly growing computational demands, motivating the development of mac
arXiv:2506.06006v3 Announce Type: replace-cross Abstract: Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given t
arXiv:2606.04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-
arXiv:2606.04032v1 Announce Type: cross Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role
arXiv:2606.04527v1 Announce Type: cross Abstract: We present Echo Infinity, an autoregressive (AR) framework towards real-time infinite video generation that employs a learnable evolving memory to dyn
arXiv:2603.16867v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but th
arXiv:2606.04342v1 Announce Type: cross Abstract: Multi-step time series forecasting (MSF) is commonly evaluated using point-wise error metrics such as mean squared error (MSE), implicitly treating th
Highlighting recent advances in multi-GPU and tensor parallel support in llama.cpp Over the last few months llama.cpp maintainers and engineers from NVIDIA collaborated to improve the multi-GPU perfor
arXiv:2606.04485v1 Announce Type: new Abstract: Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar toke
arXiv:2506.05233v2 Announce Type: replace-cross Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transfo
arXiv:2606.04343v1 Announce Type: new Abstract: Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV
arXiv:2606.04974v1 Announce Type: new Abstract: Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional conte
arXiv:2602.01027v2 Announce Type: replace Abstract: Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-preci
arXiv:2606.04000v1 Announce Type: cross Abstract: We present a probabilistic modeling framework for incorporating small-scale spatial heterogeneity into macroscopic descriptions of material behavior f
arXiv:2511.20102v3 Announce Type: replace Abstract: Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse atten
arXiv:2606.04317v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud s
arXiv:2603.09242v2 Announce Type: replace Abstract: The growing realism of generative models has blurred the boundary between real and synthetic content, posing significant challenges to reliable AI-g
arXiv:2606.03280v1 Announce Type: new Abstract: Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training. We ask whether a more d
arXiv:2606.03965v1 Announce Type: cross Abstract: Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little
arXiv:2606.03355v1 Announce Type: new Abstract: Physics models are inherently imperfect due to misspecified or missing mechanisms, resulting in systematic discrepancies between model predictions and r
arXiv:2606.02737v1 Announce Type: cross Abstract: Dense retrieval models exhibit positional bias: retrieval effectiveness degrades when relevant information appears later in a passage (Zeng et al., 20
The search results show general llama.cpp information and references to other recent builds (like b9484), but the specific details for b9487 were not clearly accessible. Based on the context from llam
arXiv:2606.03212v1 Announce Type: new Abstract: Low-rank tensor decomposition (TD) is usually effective on clean, fully observed data, but it often degrades under severe missingness or noise. Low-rank
arXiv:2606.03061v1 Announce Type: cross Abstract: Emerging distributed computing paradigms, such as the computing continuum, are inherently heterogeneous, stochastic, and complex. Efficiently and effe
arXiv:2606.03110v1 Announce Type: new Abstract: Aligning AI systems with diverse human values requires value specifications grounded in concrete examples, but generating such examples without extensiv
arXiv:2606.02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and e
arXiv:2606.03132v1 Announce Type: new Abstract: Large language models (LLMs) have shown growing potential for Cognitive Behavioral Therapy (CBT) counseling. However, most existing approaches still for
arXiv:2511.05050v3 Announce Type: replace-cross Abstract: In this study, a scalable online kernel learning framework is proposed for estimating bidirectional causal effects in systems characterized by
arXiv:2606.02791v1 Announce Type: new Abstract: Watershed networks exhibit convergent topologies in which multiple tributaries merge into downstream channels,integrating diverse upstream hydrological
arXiv:2512.11213v2 Announce Type: replace Abstract: Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, e
arXiv:2606.03188v1 Announce Type: new Abstract: Recent World Action Models (WAMs) have demonstrated impressive capabilities in embodied decision-making. However, whether their effectiveness stems from
arXiv:2606.03768v1 Announce Type: new Abstract: Extended chain-of-thought (CoT) traces improve LLM reasoning but incur substantial computational and memory costs. While existing CoT compression method
arXiv:2606.03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many s
arXiv:2606.03803v1 Announce Type: cross Abstract: We present LiveBand, a real-time system that generates high-fidelity music accompaniments to live audio input, respecting strict causal constraints. O
Anthropic's Claude 3.5 Sonnet (M3) model features sparse attention mechanisms, 1 million token context length, and multimodal capabilities, with Together AI optimizing the serving infrastructure to en
arXiv:2512.19347v3 Announce Type: replace Abstract: Robot manipulation has increasingly adopted data-driven generative policy frameworks, yet the field faces a persistent trade-off: diffusion models s
arXiv:2606.03236v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents m
arXiv:2606.03521v1 Announce Type: cross Abstract: To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversa
arXiv:2504.01250v2 Announce Type: replace Abstract: This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning a
arXiv:2606.03784v1 Announce Type: new Abstract: Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning and robotic control, but its effective form and integration strategy remain underexp
arXiv:2606.02909v1 Announce Type: cross Abstract: Gradient observations can substantially improve Gaussian process (GP) surrogates, particularly in high-dimensional settings where function evaluations
arXiv:2601.14569v2 Announce Type: replace Abstract: Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL
arXiv:2606.03075v1 Announce Type: new Abstract: Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate in
arXiv:2606.03954v1 Announce Type: new Abstract: As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible conse
arXiv:2606.00219v1 Announce Type: cross Abstract: We are witnessing a surge in observations of the cosmic dawn (CD) and epoch of reionisation (EoR), driving an increasing demand for fast and robust th
arXiv:2606.00630v1 Announce Type: new Abstract: Intraoperative ultrasound (ioUS) is a versatile, cost-effective modality in brain tumour surgery, but its interpretation is difficult: acquisition plane
arXiv:2602.18645v2 Announce Type: replace Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full