Knowledge catalogue
Timelines just got shorter... AI will understand the physical 3D space better than humans by November* Is Google so back? Their new Gemini 4 Argon understands the physical 3D world better than any oth
arXiv:2609.37605v1 Announce Type: new Abstract: Supervised deep learning has advanced sparse-view tomographic reconstruction. However, conventional models, which typically map filtered back-projection
arXiv:2609.36032v1 Announce Type: cross Abstract: Uniform random rotations are an effective preprocessing step for quantization: they make normalized coordinate distributions approximately Gaussian, e
arXiv:2609.35810v1 Announce Type: cross Abstract: Large language models are increasingly used in oncology applications, but their predictions are often weakly grounded in explicit medical structure. W
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since addi
arXiv:2609.37279v1 Announce Type: new Abstract: Neural solvers offer efficient surrogates for numerical simulation of partial differential equations (PDEs). For time-dependent problems, strong one-ste
arXiv:2609.36529v1 Announce Type: cross Abstract: Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference. The mem
We had a Dell B300 in the lab for a few weeks and used it to create two fine tunes of Qwen Flash Next. Victoria (coding and agents) Qwen3.8-Flash-Next cut down by 44% using a paper / technique called
arXiv:2603.28773v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon oft
arXiv:2609.36262v1 Announce Type: new Abstract: Recent studies have observed that parameter changes during language-model post-training can be concentrated in a small subset of coordinates. This pheno
arXiv:2609.37031v1 Announce Type: new Abstract: Building extraction from optical remote sensing (RS) imagery is fundamental to urban mapping, yet existing methods are often dataset-specific and genera
arXiv:2609.37076v1 Announce Type: new Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this iss
Hi folks, I've spent the last couple of months experimenting with Strix Halo and previously I released a proof of concept I called llama-halo-hybrid. I've continued updating it and it now performs ver
loss curve (taken from the last micro of every step, to explain the variation) some help from gemini 3.8 flash high About 40% of the way done with the initial fine tune. The loss is so spiky because I
arXiv:2609.38043v1 Announce Type: new Abstract: Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated us
Apple Foundation Model 3 through Private Cloud Compute is directly available in macOS 27.2 through familiar AI clients. For Mac users running local models such as Qwen 3.x or Gemma 4, AFM 3 PCC is a c
arXiv:2609.35916v1 Announce Type: cross Abstract: Real-world embodied agents often pursue independent objectives within a shared physical environment, where their actions can alter the conditions face
arXiv:2609.37457v1 Announce Type: new Abstract: Enterprise artificial-intelligence agents increasingly call tools, modify infrastructure, and process protected data, creating a need to separate action
arXiv:2609.37003v1 Announce Type: new Abstract: Vessel perception from space is crucial for a wide range of maritime applications, from traffic monitoring to environmental protection. However, most ex
arXiv:2609.36691v1 Announce Type: new Abstract: Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps embodi
arXiv:2609.37519v1 Announce Type: cross Abstract: Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched d
arXiv:2609.38119v1 Announce Type: new Abstract: Long-form video understanding requires multimodal agents to iteratively gather evidence over many reasoning steps. However, most existing agentic method
arXiv:2609.37709v1 Announce Type: cross Abstract: Recent multimodal image generation models can take multiple images and textual instructions as input, enabling reference-based generation guided not o
arXiv:2609.37287v1 Announce Type: cross Abstract: Image translation is a fundamental capability of multimodal models for multilingual applications, requiring visual understanding and meaning preservat
arXiv:2609.37002v1 Announce Type: cross Abstract: High-resolution visual question answering often fails because a multimodal model does not acquire the small, spatially localized evidence needed to an
arXiv:2609.36572v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further en
arXiv:2609.36648v1 Announce Type: new Abstract: Vision-language pre-training has reshaped image clustering, giving rise to language-assisted image clustering (LaIC), which leverages textual semantics
arXiv:2609.37062v1 Announce Type: cross Abstract: Dynamic layer skipping reduces LLM computation by allowing each token to execute only a subset of the model's layers. However, existing skippers rely
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
arXiv:2609.35898v1 Announce Type: cross Abstract: This paper proposes Wasserstein Causal Forests (WCF) for settings in which each unit's outcome is itself a probability distribution. This study also d
arXiv:2607.10803v2 Announce Type: replace-cross Abstract: Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and inte
arXiv:2609.37731v1 Announce Type: new Abstract: Activation space and parameter space provide complementary views of model computation. Activations represent information, while weights read, transform,
arXiv:2609.36937v1 Announce Type: cross Abstract: Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation,
arXiv:2609.37317v1 Announce Type: new Abstract: Omnimodal evaluation should go beyond independent text, image, and speech production: individually plausible outputs may not express a coherent shared e
arXiv:2609.37104v1 Announce Type: cross Abstract: Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a co
arXiv:2609.36636v1 Announce Type: cross Abstract: Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding
arXiv:2609.36881v1 Announce Type: new Abstract: Causal foundation models (CFMs) pre-trained on data generated from various structural causal models (SCMs) have been proposed for estimating causal effe
arXiv:2609.38011v1 Announce Type: new Abstract: Modern machine learning systems are trained on mixtures of data from different domains, and choosing the right mixture can substantially improve downstr
arXiv:2609.36138v1 Announce Type: new Abstract: Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clarification, answering directly, or d
arXiv:2609.36704v1 Announce Type: new Abstract: Modern learning systems often acquire supervision at multiple resolutions, trading annotation cost against information content. We study cost-aware two-
arXiv:2609.37680v1 Announce Type: cross Abstract: One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can t
arXiv:2609.36685v1 Announce Type: new Abstract: Co-speech gesture generation aims to synthesize natural gestures that are both temporally synchronized with speech and semantically consistent with the
arXiv:2609.35832v1 Announce Type: cross Abstract: Intrinsic self-correction asks a language model to revise its own answer without receiving new external evidence. A second pass can recover mistakes,
arXiv:2609.37602v1 Announce Type: cross Abstract: Robust and reliable perception is essential for autonomous robots operating in real-world environments, particularly in long-term missions where envir
arXiv:2609.37345v1 Announce Type: new Abstract: Streaming video understanding requires Video Large Language Models (Video-LLMs) to reason over continuous visual streams under causal constraints. As th
arXiv:2609.36830v1 Announce Type: new Abstract: Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation wit
arXiv:2609.37667v1 Announce Type: new Abstract: Counterfactual explanations for graph neural networks (GNNs) find the minimal intervention that flips a node's prediction--but computing one requires re
arXiv:2609.36686v1 Announce Type: new Abstract: Identifying the root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored
arXiv:2609.37755v1 Announce Type: new Abstract: Purpose: Most Greek papyri remain unpublished and undigitised; a handwritten text recognition (HTR) pipeline that transcribes them automatically would l
Hi, I’m using Qwen3.8 27B in my vulnerability scanner, it does scan JS files, tries to generate exploits etc. I’m using uncensored version, the model is like 21GB. Running it on Mac M4 Pro 64GB ram, i
arXiv:2609.37499v1 Announce Type: new Abstract: Historical archives are an under-used source for extending the instrumental climate record backward in time, and LLMs offer a way to extract the indices
arXiv:2609.36635v1 Announce Type: cross Abstract: Bug validation asks a coding agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness a
arXiv:2609.37004v1 Announce Type: new Abstract: We present World2Motion, a framework that generates scene-aware 3D human motion and corresponding video from a single image and a text prompt. While exi
arXiv:2609.36438v1 Announce Type: new Abstract: Autonomous driving requires choosing a safe and efficient plan as surrounding traffic evolves. Generate-and-select planners propose multiple trajectorie
arXiv:2609.37594v1 Announce Type: new Abstract: Uncertainty estimates tell us how unsure a model is, but not why. Without knowing which parts of an input influences a model's uncertainty, we cannot te
arXiv:2609.36837v1 Announce Type: new Abstract: Generative super-resolution models can turn portable 64 mT MRI into images that look like 3T scans, and the field evaluates them with PSNR, SSIM, and pi
arXiv:2609.36661v1 Announce Type: new Abstract: Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a
arXiv:2609.37494v1 Announce Type: new Abstract: Multiple-choice benchmarks are cheap to grade and are running out of room, and the standard remedy, writing harder items, is slow and repeated for every
arXiv:2609.37883v1 Announce Type: new Abstract: Pre-trained language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various l
arXiv:2609.34035v1 Announce Type: new Abstract: Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigati