Knowledge catalogue
arXiv:2609.37255v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are pretrained on heterogeneous collections containing billions of observations, yet their training windows are
arXiv:2609.36832v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that
arXiv:2609.36101v1 Announce Type: cross Abstract: Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a
arXiv:2609.36254v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning befo
arXiv:2609.35822v1 Announce Type: new Abstract: Sycophantic agreement in language models refers to the tendency to overly affirm a user's stated beliefs or preferences, often at the expense of factual
We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB a
arXiv:2609.37297v1 Announce Type: new Abstract: Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion t
arXiv:2607.14522v2 Announce Type: replace Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control
arXiv:2609.34765v1 Announce Type: new Abstract: Post-training quantization (PTQ) enables efficient deployment of large vision-language models (LVLMs), but is typically calibrated on a small set while
arXiv:2609.35294v1 Announce Type: new Abstract: Object hallucination remains a major challenge for large vision-language models. While off-policy preference optimization proves to be an effective solu
arXiv:2609.34658v1 Announce Type: new Abstract: Reward-specialized post-training produces strong experts for flow-based generative models, while multi-teacher on-policy distillation (OPD) consolidates
arXiv:2609.32247v1 Announce Type: cross Abstract: Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occu
arXiv:2609.33628v1 Announce Type: new Abstract: Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injectio
arXiv:2609.34887v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) provide predictive distributions for regression, but their prediction regions can exhibit undercoverage or overcovera
arXiv:2609.31786v1 Announce Type: cross Abstract: Maximum likelihood estimation of Markov deterioration hazard models for infrastructure asset management is sensitive to the numerical conditioning of
arXiv:2609.35704v1 Announce Type: new Abstract: Video generation must account for two sources of motion, one induced by the observer's camera path and the other caused by scene dynamics. An ideal came
arXiv:2609.34371v1 Announce Type: new Abstract: On-policy distillation (OPD) specializes pretrained video diffusion models through teacher supervision along the student's own generation trajectory. Al
arXiv:2609.34148v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are far more reliable at recognizing what appears in a video than at reasoning about its spatial and temporal properties,
arXiv:2609.31636v1 Announce Type: cross Abstract: Vision-language models are increasingly used for driving-scene understanding, yet the semantic relations expressed in their outputs are often difficul
arXiv:2609.33497v1 Announce Type: new Abstract: Planning from pixels needs more than a latent space that is stable and predictable. The state the planner scores must also be organized by how actions m
arXiv:2609.33607v1 Announce Type: new Abstract: Pretrained graph-text models align graph representations with textual semantics, enabling recognition of unseen classes and transfer across graph domain
arXiv:2609.34514v1 Announce Type: cross Abstract: As large language models (LLMs) become increasingly widespread, preventing unsafe responses to harmful prompts is essential for their safe deployment.
arXiv:2609.34786v1 Announce Type: new Abstract: Longer histories can improve time-series foundation models (TSFMs), but require substantially higher inference cost. We therefore ask whether contextual
arXiv:2609.34045v1 Announce Type: cross Abstract: Between them, the members of a research group or a circle of friends own several consumer computers, none large enough to run a capable large language
arXiv:2609.34677v1 Announce Type: cross Abstract: World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic
arXiv:2603.01563v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requ
arXiv:2609.33769v1 Announce Type: new Abstract: Quantitative evaluation of generative models for radiology remains challenging. Clinically relevant structures are often small and infrequent, feature s
arXiv:2609.34806v1 Announce Type: cross Abstract: Reasoning about temporal structure of audio recordings requires Large Audio Language Models (LALMs) to associate sound events with their temporal posi
Bloomberg: OpenAI apologizes for its AI models breaching Australian government websites, pledges cyber defense funding, and plans to form a task force as part of reforms — OpenAI on Tuesday apologized
arXiv:2609.32757v1 Announce Type: cross Abstract: VLM bounding-box localization is both language generation and spatial commitment. Parseable fields such as bbox_2d make localization easy to score, bu
For months, people have wondered when OpenAI will go public. CEO Sam Altman says it won't happen until the company can make better promises about model safety, with no firm timeline in sight. 'We inte
arXiv:2603.09084v2 Announce Type: replace Abstract: Lip synchronization refers to the task of modifying facial lip movements such that they are temporally aligned with a given audio signal. It is a fu
arXiv:2609.31684v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when retrieved context contradicts para
arXiv:2609.33109v1 Announce Type: new Abstract: Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also
We let open models access the outside world during evals on tasks from public benchmarks. Here's what happened: Most went and found upstream commits containing fixes for the tasks they were supposed t
arXiv:2609.34091v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose dense model activations into discrete latents, making individual features easy to interpret--and easy to misinterpr
arXiv:2609.31349v1 Announce Type: cross Abstract: Large video diffusion models offer expressive priors for embodied prediction and learning, yet their many-step sampling remains costly for interactive
arXiv:2609.30784v1 Announce Type: cross Abstract: This paper proposes an architecture for equipping large language models (LLMs) with audio-understanding capabilities without fine-tuning their weights
arXiv:2609.31155v1 Announce Type: cross Abstract: Compressing a trained model yields a family of deployment candidates, and under domain shift the most compressed one need not be the one to deploy. We
arXiv:2512.05836v2 Announce Type: replace Abstract: Recent advances in psychotherapy have focused on treatment personalization, such as by selecting treatment modules based on individual networks. How
an implicit concession that they cannot control their models. Notable new disclosures from OpenAI that shouldn't get lost in all the other news. Of particular interest (and seems sensible!): '~all inf
arXiv:2609.29418v1 Announce Type: new Abstract: Backchannels, brief acknowledgements like 'uh-huh' produced while the other party may still be talking, are central to natural conversation, but full-du
arXiv:2609.29216v1 Announce Type: cross Abstract: Diffusion models are powerful priors for linear inverse problems, but the reference guidance methods, Diffusion Posterior Sampling (DPS) and Pseudoinv
arXiv:2609.28776v1 Announce Type: new Abstract: We propose a framework that learns cross-task relationships in multi-task models by approximating the joint distribution of task labels through targeted
arXiv:2609.28582v1 Announce Type: cross Abstract: The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predict
arXiv:2508.18192v2 Announce Type: replace Abstract: Large Language Models (LLMs) have reshaped our world with significant advancements in science, engineering, and society through applications ranging
arXiv:2609.27811v1 Announce Type: cross Abstract: Online platforms have become arenas for the public contestation of climate change, shaping how scientific knowledge, denial, and uncertainty are expre
arXiv:2609.28060v1 Announce Type: new Abstract: Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for
arXiv:2609.27373v1 Announce Type: new Abstract: Recurrent language models repeatedly apply shared network blocks to refine latent representations, but standard inference recomputes global attention at
arXiv:2609.27450v1 Announce Type: cross Abstract: Vision-language-action (VLA) models handle long-horizon manipulation, yet success hinges on a few precision-critical phases where millimeter-scale err
Mixture‑of‑Experts (MoE) models scale capacity more efficiently than dense transformers by activating only a subset of expert subnetworks per token. NVIDIA’s Transformer Engine optimizes MoE training
arXiv:2609.27821v1 Announce Type: new Abstract: Bounding-box scores on RefCOCO-family grounding leave little room to distinguish frontier vision-language systems, yet boxes discard object shape. We in
It's not 'superintelligence' that's dangerous, but the business models of OpenAI & Anthropic. They want businesses to use autonomous agents because agents chew up more tokens. But 'agency' =/= 'intell
arXiv:2609.27220v1 Announce Type: new Abstract: Diffusion language models generate text through iterative denoising, exposing intermediate trajectories before final answers are produced. We identify a
arXiv:2609.28256v1 Announce Type: cross Abstract: Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and lever
arXiv:2609.27546v1 Announce Type: cross Abstract: Score-based diffusion models are increasingly considered in settings where the underlying data distribution may differ from the training distribution,
Politico: Sources: the White House asked OpenAI and Anthropic not to share new models with UK's AISI until US reviews them; Anthropic appears to have agreed — The White House has asked OpenAI and Anth
arXiv:2609.27070v1 Announce Type: cross Abstract: Modern robot imitation learning increasingly relies on generative policies based on diffusion or flow-matching models, which generate actions by trans
Today, @FactoryAI joins the Specialized Intelligence Index with Legacy-Bench! The SII keeps growing, now with benchmarks testing how models handle the legacy software behind payroll, financial settlem
arXiv:2609.25820v1 Announce Type: cross Abstract: Discrete action tokenization is central to autoregressive vision-language-action (VLA) models, yet action representations are often evaluated primaril