Knowledge catalogue
arXiv:2609.10445v1 Announce Type: new Abstract: Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: mo
arXiv:2609.09735v1 Announce Type: cross Abstract: Healthcare systems, mental health, and public well-being are increasingly affected by cyberbullying and harmful online interactions. This paper presen
arXiv:2609.07944v1 Announce Type: new Abstract: Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recover
arXiv:2609.08832v1 Announce Type: new Abstract: Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains larg
arXiv:2609.09902v1 Announce Type: new Abstract: Reading a transformer's internal states in token space is easy to do and hard to trust: a logit lens on a single hidden state is dominated, at intermedi
arXiv:2609.10479v1 Announce Type: cross Abstract: More Electric Aircraft require fast and reliable monitoring of high-frequency electrical networks, yet most power quality disturbance and fault diagno
DeepSeek-V4.1-Flash is now being rolled out on Ollama's cloud, starting with Max and Team accounts. We are quickly adding more capacity to roll it out to all subscribers. 🚀 Introducing DeepSeek-V4.1-F
arXiv:2609.09737v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from nois
arXiv:2609.08609v2 Announce Type: replace Abstract: Tracking semantic change in low-resource languages across extensive historical timelines presents significant challenges due to data scarcity and th
arXiv:2609.10387v1 Announce Type: new Abstract: Deformable convolution networks have recently become popular for many computer vision tasks, especially for semantic segmentation, because of their exce
arXiv:2609.08943v1 Announce Type: cross Abstract: Automatic fact-checking systems assess the veracity of claims given evidence from relevant documents. Large Language Models (LLMs) have demonstrated s
arXiv:2609.06731v1 Announce Type: cross Abstract: Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accuratel
arXiv:2609.08267v1 Announce Type: new Abstract: Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring fact
arXiv:2609.05806v1 Announce Type: new Abstract: Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide r
arXiv:2609.10243v1 Announce Type: new Abstract: Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world. Yet methods that perform well in sim
arXiv:2507.19364v3 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) into social simulation has generated considerable enthusiasm, but also raises substantial methodolog
arXiv:2609.10531v1 Announce Type: new Abstract: Image-to-3D models can generate visually compelling 3D assets from a single RGB image, but their geometry is often only loosely constrained by the avail
arXiv:2609.10089v1 Announce Type: new Abstract: Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for near-term quantu
arXiv:2502.00858v4 Announce Type: replace Abstract: Natural-language instructions rarely specify every detail required for embodied action. An agent asked to ``prepare an apple,'' for example, must st
arXiv:2609.09889v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR mo
arXiv:2609.10049v1 Announce Type: new Abstract: Clinical notes contain personally identifiable information (PII), restricting reuse for research and medical AI, especially when data cannot leave an in
Originally, the Transformer paper was proposed to improve Google Translate. 9 years later, as the AI industry is built on top of its architecture, we've never stopped thinking about translation. Meet
arXiv:2510.26656v4 Announce Type: replace-cross Abstract: Likelihood-free inference (LFI) enables system identification in complex tasks via black-box modelling, abstracting nonlinearity and stochasti
Part 4 of the same box. Part 1 was 17 -> 25-29 t/s with the expert cache PR, part 2 was 37-41 t/s after switching to UD-Q4_K_XL and stacking MTP on the cache, part 3 was the top-k fallback that was so
arXiv:2609.09999v1 Announce Type: new Abstract: Terminology-aware translation asks for more than a correct translation: the output must use the exact terms a glossary prescribes. The standard recipe,
arXiv:2609.09240v1 Announce Type: new Abstract: Ultra-low-bit language models promise reductions in storage and memory traffic, but a nominal '1.58-bit' label does not specify the deployed representat
arXiv:2609.10363v1 Announce Type: new Abstract: SceneHI is a framework that lifts high-resolution, illumination-aware priors from 2D diffusion models to perform 3D texture synthesis. It is the first t
arXiv:2609.09764v1 Announce Type: new Abstract: Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collabo
arXiv:2609.08003v1 Announce Type: new Abstract: Behavioral foundation models have been proposed as stand-ins for human participants across settings, but it is unclear whether theories discovered on th
arXiv:2609.09264v1 Announce Type: new Abstract: Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam,
arXiv:2506.03889v3 Announce Type: replace Abstract: When training autoregressive models to forecast dynamical systems, a critical question arises: how far into the future should the model be trained t
I initially saw CED as just an efficiency improvement, but the more I read about it, the more it feels like an inference architecture leap. The encoder/decoder split has some pretty interesting implic
arXiv:2510.08831v2 Announce Type: replace Abstract: As AI writing tools become widespread, we need to understand how both humans and machines evaluate literary style, a domain where objective standard
arXiv:2609.10210v1 Announce Type: new Abstract: How many of a transformer's components decide a token? Counted by the absolute value of each unit's and channel's contribution to the logit, one predict
arXiv:2609.09974v1 Announce Type: new Abstract: Grapheme-to-phoneme conversion (G2P) refers to the task of converting a sequence of graphemes to a corresponding sequence of phonemes. While Filipino G2
arXiv:2609.08322v1 Announce Type: cross Abstract: Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is r
arXiv:2609.09275v1 Announce Type: cross Abstract: Decays of beauty and charm hadrons provide sensitive probes of physics beyond the standard model, including decays with invisible particles, in which
arXiv:2609.10139v1 Announce Type: new Abstract: Driver gaze provides information regarding driver visual attention and situational awareness to the surrounding traffic. Existing driver gaze estimation
arXiv:2609.10244v1 Announce Type: new Abstract: We present our system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. A small (4B-parameter) VLM is fine-tuned a
arXiv:2609.06941v1 Announce Type: new Abstract: Causal effect estimation asks how an outcome would change under an intervention, and medicine, economics, and public policy all treat it as a foundation
arXiv:2609.06072v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) of mixture-of-experts (MoE) models commonly attaches a separate low-rank adapter to each expert. This expert-wise
arXiv:2609.06972v1 Announce Type: cross Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection
In September 2026 OpenAI announced that an AI‑assisted team using the Astra‑next model solved the Navier–Stokes Millennium Prize Problem in 88 hours. The effort employed roughly 10,000 agents processi
arXiv:2609.07917v1 Announce Type: new Abstract: Counterfactual explanations formalize 'what-if' scenarios by identifying modifications to an input instance that obtain a desired alternative prediction
model: fix granite3 moe unknown parameter count (#28632) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/4620980
arXiv:2609.06511v1 Announce Type: new Abstract: Physical and synthetic models may describe complementary aspects of the same PDE-governed system while receiving different, possibly fragmented, observa
arXiv:2609.05730v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation fo
arXiv:2609.08250v1 Announce Type: cross Abstract: How far a pushed object slides depends on its mass and friction, which no single image reveals. Pretrained visual encoders are increasingly used as th
arXiv:2609.07094v1 Announce Type: new Abstract: Reasoning is a promising route to the generalization that autonomous driving requires in the long tail, as it can infer how the elements of a scene depe
arXiv:2510.00527v2 Announce Type: replace Abstract: Deterministic models for 3D hand pose reconstruction, whether single-staged or cascaded, struggle with pose ambiguities caused by self-occlusions an
arXiv:2404.06349v3 Announce Type: replace Abstract: The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual re
arXiv:2609.08657v1 Announce Type: new Abstract: Charts are structured visual compositions whose elements have distinct functional roles, semantic correspondences, and visibility relations. This struct
arXiv:2606.19376v2 Announce Type: replace Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expe
arXiv:2609.05988v1 Announce Type: new Abstract: Recurrent reasoning models (RRMs) can solve structured problems, achieving easy-to-hard generalization through iterative computation in hidden space. Th
Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an Open
arXiv:2609.07369v1 Announce Type: new Abstract: We introduce DF26, a novel benchmark for detecting AI-generated videos containing fully synthetic clips produced by recent text-to-video and image-to-vi
arXiv:2609.08331v1 Announce Type: new Abstract: Video Large Language Models (VideoLLMs) are increasingly deployed in safety-critical applications such as content moderation and video analytics. To pro
arXiv:2609.06962v1 Announce Type: new Abstract: Real-world remote sensing image dehazing (RSID) remains challenging because atmospheric scattering, spatially non-uniform haze and colour distortion joi
arXiv:2609.05539v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as genera
arXiv:2609.08025v1 Announce Type: cross Abstract: Reasoning agents increasingly rely on external tools such as web search to answer complex queries. Reinforcement learning (RL) finetuning algorithms s