Knowledge catalogue
arXiv:2609.07051v1 Announce Type: new Abstract: World models increasingly serve as the predictive core of model-based reinforcement learning agents, enabling them to simulate future dynamics and reaso
arXiv:2609.06591v1 Announce Type: new Abstract: Developing unified physics-based humanoid controllers that can navigate complex 3D scenes and manipulate objects remains a longstanding challenge. Exist
arXiv:2609.07178v1 Announce Type: new Abstract: Deep learning models for CT scan analysis are often limited by the scarcity of precise pixel-level annotations, which require significant radiologist ef
Why are AI employees willing to gamble with our lives? Many AI employees hold a misanthropic belief: a cosmos of blissful AIs is worth risking human extinction. Utilitarians shouldn't decide the fate
arXiv:2609.07002v1 Announce Type: new Abstract: Generalizable and robust dexterous in-hand manipulation requires a policy to infer object pose, geometry, contact, and potential slip from partial and n
I was reading up on the recent controversy around Tristan Buckmaster, Levent Alpöge, OpenAI, and the Navier–Stokes result, and it got me thinking about something broader than this particular dispute.
I don't think anyone posted about this here, but Qwen released a finetuned version of 3.5 4 for driving. The full Bf16 checkpoint is 9B. This is a very interesting development of Chinese AI labs tackl
arXiv:2609.04267v1 Announce Type: new Abstract: Aerodynamic surrogate models trained on high-fidelity CFD data reproduce numerical predictions of both scalar outputs and entire fields accurately, yet
arXiv:2609.05400v1 Announce Type: new Abstract: When there is not enough labeled data to properly train deep learning models, transfer learning can help. We still do not fully understand how effective
arXiv:2609.04303v1 Announce Type: cross Abstract: Information abstraction, which groups strategically similar private states into a tractable number of buckets, is essential for scaling game-solving a
arXiv:2602.11558v2 Announce Type: replace Abstract: Brain foundation models (BFMs) are advancing neurotechnology by learning transferable representations from neural signals, with broad potential in c
arXiv:2609.04531v1 Announce Type: new Abstract: Language generation is almost universally treated as a sequential process: autoregressive models emit one token at a time, while diffusion language mode
arXiv:2609.04362v1 Announce Type: cross Abstract: Music audio-language models are evaluated almost entirely by accuracy on multiple-choice questions. This protocol forces the model to commit to an opt
arXiv:2609.04942v1 Announce Type: new Abstract: Instruction-guided 3D editing is essential for interactive content creation, yet it faces a significant bottleneck: the severe scarcity of high-quality
arXiv:2609.05303v1 Announce Type: new Abstract: Hyperspectral and multispectral image fusion (HMIF) aims to reconstruct a high-resolution hyperspectral image (HR-HSI) by combining the fine spatial det
The Guardian: Matt Clifford steps down as the chair of the UK government's science and tech research unit after joining Anthropic, following conflict of interest concerns — Matt Clifford forced to sta
arXiv:2609.04958v1 Announce Type: new Abstract: Recovering camera and hand motion in world coordinates from egocentric video is a key capability for activity understanding, robot learning, and augment
arXiv:2609.05070v1 Announce Type: new Abstract: Automated gastrointestinal (GI) endoscopy classification requires models that generalize across diverse modalities and class distributions, often far fr
arXiv:2609.04921v1 Announce Type: cross Abstract: Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that
arXiv:2609.04837v1 Announce Type: new Abstract: Single domain generalization (SDG) aims to learn a model from one labeled source domain that generalizes to unseen target domains. A common strategy is
arXiv:2609.05235v1 Announce Type: cross Abstract: Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language
arXiv:2609.04793v1 Announce Type: new Abstract: Proteins perform diverse cellular functions, and even single amino-acid substitutions can alter stability, activity, or molecular interactions. Protein
arXiv:2609.04893v1 Announce Type: new Abstract: Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation,
arXiv:2609.04634v1 Announce Type: cross Abstract: As generative audio models grow in complexity, the computational and ecological costs of synthesizing everyday sounds have become increasingly prohibi
arXiv:2603.27520v2 Announce Type: replace Abstract: In video diffusion transformers, visual patch tokens maintain explicit correspondence to space and time. We hypothesize that their channel dimension
arXiv:2609.04637v1 Announce Type: cross Abstract: Audio Large Language Models (Audio LLMs) have advanced in audio understanding, yet they can still predict the answer by reasoning from textual cues or
arXiv:2609.05376v1 Announce Type: cross Abstract: Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacl
Reasoning from scratch round 2: In this video, I cover the text generation process in LLMs and KV caching (to prepare the base model before adding reasoning techniques in the upcoming ones). 00:00 Int
Banger paper from Microsoft and Cornell. If you have looked at thinking tokens and decided you cannot afford the context, read this one. (bookmark it) A pause token buys the model extra compute for ea
arXiv:2609.03992v1 Announce Type: new Abstract: We present Alignment-Free Text-Audiobox (Text-AB), a unified framework for high-quality voice dubbing and full-duplex dialogue synthesis. Building on a
arXiv:2609.04070v1 Announce Type: new Abstract: Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a
arXiv:2609.03522v1 Announce Type: cross Abstract: Semantic ID (SID) generative recommendation predicts the next item by generating a short tuple of discrete tokens. Recent masked-diffusion methods imp
arXiv:2609.03629v1 Announce Type: cross Abstract: Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated tr
arXiv:2405.07338v2 Announce Type: replace-cross Abstract: Early detection of vision-threatening conditions such as diabetic retinopathy, glaucoma, and age-related macular degeneration depends on retin
arXiv:2609.03611v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly used to evaluate robot manipulation outcomes, but existing benchmarks offer limited evidence of cross-d
arXiv:2609.03807v1 Announce Type: cross Abstract: A free pause token gives a language model extra compute to form each next-token prediction (as a pause, or thinking, token does) but carries that comp
arXiv:2609.03889v1 Announce Type: cross Abstract: Contact-rich loco-manipulation requires a bridge between semantic action generation and physical interaction control. Existing Vision-language-action
arXiv:2609.04105v1 Announce Type: new Abstract: Blackwell's 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies domin
Introducing Z1T: Our first family of transformer-like models made for sparse probabilistic hardware like Z1 Achieving up to 140x energy efficiency gains over GPUs and revealing a new scaling law for s
arXiv:2609.03967v1 Announce Type: cross Abstract: Several studies have evaluated the ability of Large Language Models (LLMs) for meal planning, yielding positive outcomes. These models can process nat
arXiv:2609.03117v1 Announce Type: cross Abstract: Neural fields (NFs) map continuous coordinates to signals such as color or density, but fast high-quality reconstruction from sparse observations rema
arXiv:2609.04180v1 Announce Type: cross Abstract: Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We posit that auxiliary views, reformulati
arXiv:2609.03406v1 Announce Type: new Abstract: Recent years have witnessed growing interest in continual anomaly detection for industrial visual inspection. However, real-world manufacturing environm
arXiv:2609.03694v1 Announce Type: new Abstract: Implicit neural representations (INRs) can model continuous 3D shapes with a shared coordinate decoder and per-instance latent codes. At test time, auto
arXiv:2609.03503v1 Announce Type: new Abstract: With the rapid development of the Internet of Things, computation intensive directed acyclic graph (DAG) tasks have become increasingly common in cloud-
arXiv:2603.09968v2 Announce Type: replace Abstract: Online novel view synthesis requires a model to reconstruct a scene causally from a stream of observations while keeping it renderable at every mome
arXiv:2609.03695v1 Announce Type: new Abstract: Sign language dictionaries are essential resources for sign language learners, yet automatically retrieving a sign from a dictionary, given only a query
arXiv:2609.03813v1 Announce Type: new Abstract: Real-world image super-resolution (SR) increasingly relies on Diffusion Transformer (DiT) backbones, whose internal activations can be dominated by a sm
arXiv:2609.04071v1 Announce Type: cross Abstract: Pathology foundation models improve transferable representation learning for histopathology, but recent gains often rely on encoders with hundreds of
arXiv:2609.03622v1 Announce Type: cross Abstract: Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under mismatched acoustic conditions, without requirin
arXiv:2609.03090v1 Announce Type: new Abstract: Continuous chain-of-thought models compress reasoning into latent tokens. Matrix-valued variants, which route each latent token through a d x d matrix b
arXiv:2609.02991v1 Announce Type: new Abstract: Learned graph simulators provide an efficient alternative to high-fidelity solvers for granular dynamics. However, granular motion depends strongly on i
arXiv:2609.03429v1 Announce Type: new Abstract: Answering what-if queries about a scene with a VLM usually means injecting the assumption as text or repainting the scene with a generative model. We in
arXiv:2609.02210v1 Announce Type: new Abstract: Portable ultra-low-field (ULF) MRI can expand access to pediatric neuroimaging, but segmentation at 0.064 T remains challenging because anatomical bound
arXiv:2609.01673v1 Announce Type: cross Abstract: Activity-cliff ranking remains difficult because local structural changes can cause large activity differences, while high-quality data that resolve t
arXiv:2609.01795v1 Announce Type: new Abstract: Vision-language object detectors (VLODs) achieve strong zero-shot performance but remain vulnerable to distribution shifts during deployment. Mean-teach
arXiv:2609.02111v1 Announce Type: cross Abstract: Dermatology artificial intelligence (AI) models are predominantly trained on light-skinned, cancer-focused image collections, yet they are increasingl
arXiv:2506.00290v2 Announce Type: replace Abstract: This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs
arXiv:2609.02163v1 Announce Type: new Abstract: Information-theoretic measures derived from autoregressive language models are widely used to characterize the expectations that shape human reading, bu
arXiv:2603.06662v3 Announce Type: replace Abstract: Continual VideoQA with multimodal LLMs remains challenging because sequential adaptation induces task interference, while storing task-specific prom