Knowledge catalogue
arXiv:2510.08928v2 Announce Type: replace Abstract: Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce
arXiv:2609.17888v1 Announce Type: cross Abstract: We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This pro
arXiv:2609.18284v1 Announce Type: new Abstract: In recent years, three initiatives have emerged to develop generative language models in Hungary. The motivation behind them is the same. For Hungarian,
arXiv:2609.14811v1 Announce Type: new Abstract: We introduce Crypto Accounting Bench (CAB), a benchmark for assessing whether frontier and open-weight language models can reconstruct the complete jour
Dense models activate all of their parameters for each token, whereas a Mixture‑of‑Experts (MoE) model loads all experts into memory but activates only a subset—e.g., Nemotron 3.5 Lightning has 30 B t
arXiv:2609.13194v1 Announce Type: cross Abstract: A large literature builds physical structure into learned dynamics on the premise that models respecting the underlying physics predict better. We tes
arXiv:2609.13680v1 Announce Type: new Abstract: Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference model, which can degrade existing capab
arXiv:2511.09665v1 Announce Type: cross Abstract: Deep tabular modelling increasingly relies on in-context learning where, during inference, a model receives a set of (x,y) pairs as context and predic
arXiv:2609.13486v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectivenes
arXiv:2609.15013v1 Announce Type: new Abstract: Guardrail models are classifiers deployed to screen malicious prompts and responses in LLM-based services. To meet latency constraints, many lightweight
arXiv:2609.13395v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become a widely adopted architecture for Large Language Models (LLMs), as it improves model capacity while limiting compu
arXiv:2609.14168v1 Announce Type: cross Abstract: Context parameterization enables large language models (LLMs) to internalize contexts into reusable model parameters, avoiding repeated processing acr
arXiv:2609.12623v1 Announce Type: cross Abstract: Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplo
arXiv:2609.09553v1 Announce Type: cross Abstract: Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypas
arXiv:2609.11878v1 Announce Type: new Abstract: Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detectio
arXiv:2609.11242v1 Announce Type: new Abstract: Video generation has advanced to produce visually compelling and temporally coherent results. Yet, whether these models can genuinely think with video--
arXiv:2609.11548v1 Announce Type: new Abstract: Autoregressive video world models enable interactive, long-horizon exploration, but flexible control remains challenging. Exploring a source video from
arXiv:2408.10608v2 Announce Type: replace Abstract: Large language models (LLMs) may encode biased associations from heterogeneous training corpora that are not immediately visible under ordinary prom
arXiv:2504.18376v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, a
arXiv:2609.06085v1 Announce Type: cross Abstract: Understanding the joint dynamics of prices and trades is central to market microstructure, where returns and order flow interact through nonlinear and
arXiv:2609.07662v1 Announce Type: cross Abstract: Large language models are increasingly used as sources of advice and information, including in high-stakes settings, yet little is known about how the
arXiv:2609.09790v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) large-scale deployment in industrial warehouse settings specifically necessitates that models exhibit human-expert-leve
arXiv:2609.07598v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly shape communication, learning, work, creativity, and decision-making, yet social-science research on these d
arXiv:2609.10016v1 Announce Type: cross Abstract: We introduce MetroLLM-Bench, a 955-case benchmark for testing language models as the policy layer of a transit kiosk. It covers six real metro systems
arXiv:2606.14199v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven p
arXiv:2507.15824v2 Announce Type: replace Abstract: Text-to-video (T2V) models now produce striking visuals, yet they routinely violate everyday physics; objects float, tools are misused, and causal s
arXiv:2609.06011v1 Announce Type: cross Abstract: Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-modal conflict remains underexpl
arXiv:2609.03067v1 Announce Type: new Abstract: World models are an emerging paradigm in representation learning in which an agent jointly learns state-action dynamics and observation models from offl
arXiv:2609.04200v1 Announce Type: new Abstract: Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate, object scale, and camera calibrati
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
The preview releases of Solaris and GWM 2 Worlds this week are just a glimpse of what happens when video world models are scaled significantly and paired with real-time inference. It's a real-time sim
This work introduces diffusion-augmented LLMs, a new class of models. They first suggest that speculative decoding needs a separate draft model. Diffusion LLMs give up the quality of the model they re
arXiv:2609.03410v1 Announce Type: new Abstract: Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and posing unique challenges for computational models, parti
arXiv:2609.02277v1 Announce Type: cross Abstract: Perceptual illusions have long served as crucial probes into human cognition, revealing biases and limitations of perception. In the auditory domain,
Congrats to the team! Bullish on open models and all the partners we make along the way! ❤️ Let’s go Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelera
arXiv:2609.02707v1 Announce Type: new Abstract: Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to
arXiv:2609.01691v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introduce FAIRLENS, a benchmark and evaluation framework fo
arXiv:2607.09791v2 Announce Type: replace-cross Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.cpp, and a dozen further engines) b
arXiv:2609.01772v1 Announce Type: new Abstract: Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vis
Side note: when we released ARC-AGI-3 in March, and frontier models scored <1% on it, a few Singularitarian poasters took it as a personal insult, and got very worked up about it. They argued the benc
arXiv:2609.01600v1 Announce Type: cross Abstract: Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a loc
arXiv:2609.00048v1 Announce Type: cross Abstract: GUI world models are increasingly evaluated as one-step next-screen predictors, yet their intended use is often as multi-step environments for GUI age
arXiv:2609.00727v1 Announce Type: cross Abstract: Audio language models are designed to understand speech, yet it remains unclear whether they capture how something is said beyond what is said. We pre
arXiv:2609.00654v1 Announce Type: new Abstract: We describe the SciTrue team's participation in both subtasks of the NTCIR-19 SciClaimEval task~ite{sciclaimeval}, which asks systems to verify scientif
arXiv:2609.01607v1 Announce Type: new Abstract: While unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model, functional unification does not guaran
arXiv:2608.29208v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging internet
arXiv:2608.30327v1 Announce Type: new Abstract: Fine-tuning can improve legal question-answering accuracy without improving how models use law supplied in context. We study this distinction in bilingu
arXiv:2608.29431v1 Announce Type: new Abstract: Localized Representation Steering (LRS) is widely used to correct reasoning pathologies in large language models. However, standard benchmark evaluation
arXiv:2608.28623v1 Announce Type: cross Abstract: Large multimodal reasoning models (LMRMs) are getting increasingly capable, primarily through generating explicit chain-of-thought reasoning before an
arXiv:2608.29647v1 Announce Type: new Abstract: To mitigate the time complexity of generative models, one-step generative models have recently emerged through direct mapping from noise to data in a si
arXiv:2608.30567v1 Announce Type: new Abstract: We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-con
arXiv:2608.30390v1 Announce Type: new Abstract: Accurate uncertainty estimation is essential for machine learning systems de- ployed in high-stakes domains such as medicine. Traditional approaches pri
arXiv:2607.18084v2 Announce Type: replace Abstract: Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear predictio
arXiv:2608.27661v1 Announce Type: new Abstract: In Retrieval-Augmented Generation (RAG), retrieval may provide insufficient or conflicting information needed to answer a question. The system should no
arXiv:2411.10997v2 Announce Type: replace-cross Abstract: We consider the problem of learning models of spatial density functions, representing the steady-state density of mobile nodes moving on a two
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly grow
arXiv:2608.28138v1 Announce Type: new Abstract: Adapting video vision-language models (VLMs) is computationally expensive because video inputs produce a large number of visual tokens, making both fine
arXiv:2608.27406v1 Announce Type: cross Abstract: State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpu
arXiv:2608.27004v1 Announce Type: new Abstract: Reliable evaluation of vision-language models (VLMs) and medical vision-language models (Medical-VLMs) requires calibrated confidence, particularly unde
arXiv:2608.27199v1 Announce Type: new Abstract: Vision generative artificial intelligence (AI) has emerged as one of the most rapidly advancing areas of deep learning. The explosion of multimodal mode