Knowledge catalogue
arXiv:2603.27146v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals re
arXiv:2507.16116v2 Announce Type: replace Abstract: The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchroniz
arXiv:2605.24229v1 Announce Type: new Abstract: Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's
arXiv:2605.23893v1 Announce Type: new Abstract: We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer block
arXiv:2605.21573v1 Announce Type: new Abstract: We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with
arXiv:2605.12334v2 Announce Type: replace Abstract: Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to ad
arXiv:2410.04155v2 Announce Type: replace Abstract: How to defend large language models (LLMs) from generating toxic content is an important research area. Yet, most research focused on various model
arXiv:2512.23461v2 Announce Type: replace-cross Abstract: Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values
arXiv:2605.19150v1 Announce Type: cross Abstract: State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's tra
arXiv:2605.18058v1 Announce Type: new Abstract: Arabic handwriting recognition (AHR) has made significant progress with deep learning models. AHR research has largely focused on performance, with secu
arXiv:2605.16090v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the at
arXiv:2603.07514v3 Announce Type: replace-cross Abstract: Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with
arXiv:2509.12266v2 Announce Type: replace-cross Abstract: We introduce Genome-Factory, the first integrated Python library for tuning, deploying, and interpreting genomic foundation models. Our core c
arXiv:2605.15208v1 Announce Type: cross Abstract: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deploy
arXiv:2511.08565v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in social contexts, motivating analysis of how they express and shift moral judgments. In th
arXiv:2605.15071v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work ident
arXiv:2605.14890v1 Announce Type: new Abstract: Foundation models tokenize Ukrainian legal text with vastly different efficiency, yet no systematic comparison exists for this domain. We benchmark seve
arXiv:2605.13548v1 Announce Type: cross Abstract: Existing robotic foundation models, while powerful, are predicated on an implicit assumption of temporal homogeneity: treating all actions as equally
arXiv:2510.01502v2 Announce Type: replace-cross Abstract: Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social in
arXiv:2605.12678v1 Announce Type: new Abstract: Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, a
arXiv:2509.23800v3 Announce Type: replace-cross Abstract: Modern generative AI models, such as diffusion and flow matching models, can sample from rich data distributions. However, many applications,
arXiv:2605.09751v1 Announce Type: new Abstract: Trainable input embedding tables are a standard component of modern language models. We ask whether they are actually necessary at the input interface.
arXiv:2605.06366v2 Announce Type: replace Abstract: Diffusion language models (DLMs) have recently emerged as competitive alternatives to autoregressive (AR) language models, yet differences in their
arXiv:2411.08443v2 Announce Type: replace-cross Abstract: Machine unlearning is an emerging technology that removes a subset of the training data from a trained model without significantly affecting t
A year ago, frontier models started losing track of instructions somewhere around 200–300 simultaneous constraints. With 2026 models, that ceiling is closer to 2,000 — an order-of-magnitude jump. We r
arXiv:2505.19519v3 Announce Type: replace Abstract: Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the mod
arXiv:2605.08578v1 Announce Type: cross Abstract: Developing generalist systems that retain human-like data efficiency is a central challenge. While world models (WMs) offer a promising path, existing
arXiv:2512.24601v3 Announce Type: replace Abstract: We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive
arXiv:2509.08461v3 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstruct
arXiv:2605.06841v1 Announce Type: new Abstract: In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically learn a
arXiv:2510.04850v3 Announce Type: replace-cross Abstract: Reasoning distillation has emerged as a prevailing paradigm for transferring reasoning capabilities from large reasoning models to small langu
arXiv:2512.15567v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet prevailing science benchmarks probe decontextualized knowledge and
arXiv:2605.06672v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are commonly assumed to reduce shallow heuristic biases by thinking care
arXiv:2605.07632v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavi
arXiv:2601.23143v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-
arXiv:2505.18244v3 Announce Type: replace Abstract: Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale,
arXiv:2605.04989v1 Announce Type: new Abstract: Wildfire burned-area mapping is essential for damage assessment, emissions modeling, and understanding fire-climate interactions across diverse ecologic
arXiv:2605.04566v1 Announce Type: cross Abstract: Recent studies have shown that large generative models can solve vision tasks they were not explicitly trained for. However, existing evidence relies
arXiv:2605.04352v1 Announce Type: new Abstract: We introduce a benchmark suite for evaluating structural mathematical reasoning in language models, built on subgroup-construction problems in SL(3, Z)
arXiv:2508.19651v2 Announce Type: replace Abstract: AI tasks in the car interior like identifying and localizing externally introduced objects is crucial for response quality of personal assistants. H
arXiv:2605.03941v1 Announce Type: new Abstract: Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable env
arXiv:2509.17677v2 Announce Type: replace Abstract: Large language models (LLMs) have shown strong performance on mathematical reasoning under well-defined conditions. However, real-world engineering
arXiv:2605.03578v1 Announce Type: cross Abstract: Boltzmann Machines trained on evolutionary sequence data have emerged as a powerful paradigm for the data-driven design of artificial proteins. Howeve
arXiv:2605.02404v1 Announce Type: new Abstract: Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as
arXiv:2605.01018v1 Announce Type: new Abstract: Using multimodal foundation models to analyze table images is a high-value yet challenging application in consumer and enterprise scenarios. Despite its
deepagents-cli is quietly becoming the best place to start coding with open weight models. we've been investing heavily in making it a harness that's truly model-agnostic, without compromising perform
arXiv:2605.00689v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety in diverse regulatory and cultural environments
arXiv:2605.00754v1 Announce Type: cross Abstract: Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time sc
arXiv:2604.26985v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process. In standard masked diffusion, if
arXiv:2604.25273v1 Announce Type: new Abstract: Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus
arXiv:2509.17625v2 Announce Type: replace Abstract: In this paper, we present the first systematic comparison of Data Assimilation (DA) and Likelihood-Based Inference (LBI) in the context of an Agent-
arXiv:2604.24818v1 Announce Type: new Abstract: Bayesian finite mixture models can identify discrete risk clusters (low-risk vs. high-risk equipment), but face three critical bottlenecks: (1) insuffic
arXiv:2510.16340v2 Announce Type: replace Abstract: Recent advances in post-training techniques have endowed Large Language Models (LLMs) with enhanced capabilities for tackling complex, logic-intensi
arXiv:2509.06027v3 Announce Type: replace-cross Abstract: With the development of large-scale diffusion-based and language-modeling-based generative models, impressive progress has been achieved in te
arXiv:2604.23424v1 Announce Type: cross Abstract: Evolve pairs a small local language model with a persistent, teacher-compiled knowledge store -- refined through sleep consolidation and usage-driven
arXiv:2604.24391v1 Announce Type: new Abstract: Vision-Language-Navigation (VLN) models exhibit excellent navigation accuracy but incur high computational overhead. Token caching has emerged as a prom
arXiv:2604.22817v1 Announce Type: cross Abstract: Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond tr
arXiv:2604.24002v1 Announce Type: cross Abstract: Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding.
arXiv:2505.11772v3 Announce Type: replace Abstract: We introduce LAMP (Local Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how r
arXiv:2603.14882v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precisi