Knowledge catalogue
arXiv:2609.39263v1 Announce Type: new Abstract: A concept subspace's effect on model behavior does not establish how it relates to the output readout. We introduce a two-sided geometric diagnostic tha
arXiv:2609.38819v1 Announce Type: cross Abstract: Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimul
arXiv:2504.04711v2 Announce Type: replace Abstract: Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes defini
arXiv:2609.39323v1 Announce Type: cross Abstract: Robot demonstration generation requires a system to identify where an interaction should occur, plan a feasible motion, and execute the required conta
arXiv:2609.38523v1 Announce Type: cross Abstract: Financial forecasting from earnings conference calls requires models to reason over complex corporate disclosures, market expectations, and subtle com
arXiv:2609.39437v1 Announce Type: new Abstract: Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coor
arXiv:2609.38587v1 Announce Type: new Abstract: Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG founda
arXiv:2609.39130v1 Announce Type: new Abstract: Accurate assessment of color differences is essential for applications ranging from digital design to quality control. While existing color difference m
arXiv:2609.32923v2 Announce Type: replace Abstract: Wireless digital twins (DTs) rely on 3D environment models to predict radio propagation and support wireless-network decisions, yet these models are
Hybrid search, reranking, query decomposition, and query expansion are often treated as must-haves for good RAG. We wanted to see how much each actually helped, so we tested them. Same model, same emb
We spent a lot of time streamlining the process to go from your agent's trajectories to an SFT'd model on your training/inference provider of choice so you don't have to stitch together the steps manu
model : support classifier_pooling for rerankers (#29627) model : support classifier_pooling for ModernBERT rerankers Assisted-by: Claude Opus 5.5 model : read classifier pooling type in load_hparams
arXiv:2609.37400v1 Announce Type: new Abstract: Generating realistic 3D dance from music is a challenging task that requires accurate synchronization with musical rhythms while capturing the spatial c
arXiv:2609.36609v1 Announce Type: cross Abstract: Electroencephalography (EEG) analysis requires careful choices in preprocessing, statistical modeling, and machine learning because EEG signals are hi
arXiv:2609.38036v1 Announce Type: cross Abstract: Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with
arXiv:2609.36748v1 Announce Type: new Abstract: Knowledge editing enables rapid updates of specific factual knowledge in large language models (LLMs) without full retraining. However, more realistic s
arXiv:2609.38123v1 Announce Type: new Abstract: World simulation is inherently multisensory, demanding synchronized visual and acoustic dynamics in real time. Yet prevailing interactive world models r
arXiv:2609.36154v1 Announce Type: new Abstract: General-purpose models promise sensor-based decisions without training a task-specific classifier, which could reduce the dependence of Human Activity R
arXiv:2609.37970v1 Announce Type: cross Abstract: World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily im
arXiv:2609.37587v1 Announce Type: cross Abstract: Longitudinal electronic health record (EHR) modeling requires integrating new visits with an expanding patient history. Yet the continual accumulation
arXiv:2609.36813v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. Howe
arXiv:2609.37638v1 Announce Type: new Abstract: Current explanation methods for contrastive vision--language models such as CLIP mainly identify important regions without showing how to change the inp
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
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
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:2609.36438v1 Announce Type: new Abstract: Autonomous driving requires choosing a safe and efficient plan as surrounding traffic evolves. Generate-and-select planners propose multiple trajectorie
I’m building a Polish General purpose legal Model that drafts documents, answers questions using legal sources, and has enough coding ability to handle some automation. The workflow is very tool-heavy
arXiv:2609.31877v1 Announce Type: cross Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite e
arXiv:2609.33254v1 Announce Type: new Abstract: Understanding how drugs interact with protein targets is fundamental to drug discovery, drug repurposing and the early identification of promising thera
arXiv:2609.35152v1 Announce Type: cross Abstract: Successive weaving segments (SWSs) on urban expressways are bottlenecks prone to recurrent congestion and collisions, requiring fine-grained active tr
arXiv:2609.34792v1 Announce Type: new Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VL
arXiv:2609.32193v1 Announce Type: new Abstract: Vision Language Action (VLA) models condition actions directly on current visual and language context, without an explicit account of how the scene evol
arXiv:2609.31726v1 Announce Type: new Abstract: Collaborative medical AI platforms allow researchers to train models on sensitive imaging data while restricting data export. However, trained models ca
arXiv:2609.33585v1 Announce Type: new Abstract: The rapid proliferation of highly realistic AI-Generated Content (AIGC) necessitates robust and interpretable detection mechanisms. However, existing de
OpenAI: OpenAI is adopting a structured “safety case” documentation framework modeled after industries like aviation and nuclear power to govern frontier RL training — Loading... We believe we are ent
arXiv:2609.34314v1 Announce Type: new Abstract: Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether
arXiv:2609.34768v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) radar enables privacy-preserving human perception, but the extreme sparsity of point clouds from commercial single-chip senso
arXiv:2603.18095v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is a practical path to deploy large diffusion models, but quantization noise can accumulate over the denoising traj
We have released Qwen3.8-Flash-Next quantized with GSQ and RCO, together with a second, capability-targeted build in which half of the model's experts have been removed. Flash-Next is a sparse mixture
arXiv:2609.35311v1 Announce Type: new Abstract: Action-conditioned video world models predict future robot interactions from multiple cameras, yet their outputs remain disparate video collections rath
arXiv:2609.33667v1 Announce Type: new Abstract: Attributing and controlling model behavior during training requires identifying each example's contribution quickly enough to act before the next update
arXiv:2609.34596v1 Announce Type: new Abstract: Rapid and accurate burn scar delineation from satellite imagery is essential for post-fire damage assessment. Sentinel-3 OLCI, with daily revisit and 21
arXiv:2609.34123v1 Announce Type: new Abstract: Stream-level flow matching replaces the linear interpolant of conditional flow matching (CFM) by a Gaussian-process (GP) stream connecting each source--
arXiv:2609.34771v1 Announce Type: cross Abstract: Reliable AI safeguards require both control mechanisms that reduce unsafe behavior and monitoring mechanisms that detect safety risks during model int
arXiv:2609.31546v1 Announce Type: new Abstract: Electrocardiogram (ECG) foundation models typically tokenize the signal into fixed-length patches that ignore cardiac structure, so a patch may split a
arXiv:2609.30880v1 Announce Type: new Abstract: Time series foundation models (TSFMs) are pretrained on series from diverse domains, where demand series make up only a small fraction. Demand data has
arXiv:2609.31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We examine how changes in accuracy and training objec
arXiv:2609.30973v1 Announce Type: new Abstract: Lipschitz continuity is a fundamental principle in the design of certifiably robust deep neural networks (DNNs), wherein adjusting the Lipschitz constan
arXiv:2609.30967v1 Announce Type: new Abstract: Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model tha
arXiv:2609.31121v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety technique for reasoning models, enabling detection of problematic reasoning before models act. A
I know most people here probably don't care as much about sonnet 5.5 as they did opus 5.5, because their 100 and 200 plans already give them plenty of weekly usage for opus. But keep in mind: free use
arXiv:2609.31448v1 Announce Type: cross Abstract: Clinical prediction models estimate risk from patient measurements, while large language models support medical text understanding and question answer
A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a frontier LLM today? My recommendation was: start with an existi
The Top AI Papers of the Week (September 21 - 27): - HySparse2 - EvoOntology - Harness-Zero - JEV-as-a-Judge - Wiki Foundation Model - Self-Organizing Agent Teams - Self-Improvement via Fast Tree-sear
Madison Mills / Axios: Sources: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking — OpenAI, Anthrop
arXiv:2609.29433v1 Announce Type: cross Abstract: Background: Artificial intelligence (AI)-based glaucoma detection from colour fundus photographs (CFP) offers scalable screening, but performance may
arXiv:2609.29167v1 Announce Type: new Abstract: Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final re
arXiv:2602.04489v2 Announce Type: replace Abstract: Temporarily ambiguous garden-path sentences ('While the team trained the striker wondered... ') are known to cause processing difficulty, which can
arXiv:2609.28554v1 Announce Type: new Abstract: We introduce the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5, respectively, and
arXiv:2609.28927v1 Announce Type: new Abstract: World action models (WAMs) that use future visual prediction at inference time incur substantial generation costs. Asynchronous execution reduces waitin