Knowledge catalogue
arXiv:2506.18543v2 Announce Type: replace-cross Abstract: The rapid proliferation of Large Language Models (LLMs) has heightened concerns regarding their exposure to jailbreak attacks, which craft adv
arXiv:2602.23916v2 Announce Type: replace-cross Abstract: The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medi
arXiv:2605.24292v1 Announce Type: new Abstract: Log-likelihood is a standard metric for evaluating generative models. Unfortunately, in contrast to autoregressive models (ARMs), discrete diffusion mod
arXiv:2605.25313v1 Announce Type: cross Abstract: World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions.
arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP
arXiv:2508.07849v2 Announce Type: replace Abstract: Despite advances in legal NLP, no comprehensive evaluation of Transformer-based models customized for legal tasks (referred to as `legal-specific' m
arXiv:2605.23778v1 Announce Type: cross Abstract: Could it be that AI weather models are solving physical equations, although they may not be the equations used by conventional NWP models? We compute
arXiv:2605.22870v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does C
arXiv:2605.21773v1 Announce Type: cross Abstract: Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing an
arXiv:2605.22717v1 Announce Type: cross Abstract: Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline mode
arXiv:2605.21805v1 Announce Type: cross Abstract: State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the esti
arXiv:2605.22732v1 Announce Type: cross Abstract: We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationali
Jeremy Howard comments on comparative performance trends between GPT 5.5 and Claude models, noting that GPT 5.5 appears to be improving in a particular capability while Claude models are declining in
arXiv:2602.01851v2 Announce Type: replace Abstract: Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In
arXiv:2602.23200v2 Announce Type: replace-cross Abstract: When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where outp
arXiv:2605.21491v1 Announce Type: cross Abstract: As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and fil
arXiv:2602.00122v2 Announce Type: replace Abstract: In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive mann
arXiv:2605.21924v1 Announce Type: new Abstract: On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. W
arXiv:2605.20521v1 Announce Type: new Abstract: Fine-tuning adapts a pretrained machine learning model to a small, sensitive dataset, but this process risks memorizing individual new data points, maki
arXiv:2605.20777v1 Announce Type: new Abstract: Visual storytelling with diffusion models has made impressive strides in maintaining character consistency across narrative scenes. However, a critical
arXiv:2602.08819v2 Announce Type: replace-cross Abstract: Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to
arXiv:2605.20591v1 Announce Type: new Abstract: Medical large language models (LLMs), including custom medical GPTs (MedGPTs) and open-source models, are increasingly deployed on web platforms to prov
arXiv:2605.20316v1 Announce Type: new Abstract: Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified visi
arXiv:2605.20469v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible b
arXiv:2409.04777v4 Announce Type: replace Abstract: Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter sele
arXiv:2605.20774v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, but their real-world evaluation remains limited
arXiv:2605.20306v1 Announce Type: new Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous
arXiv:2605.19020v1 Announce Type: new Abstract: Vision foundation models have demonstrated strong transferability across diverse visual recognition tasks and are increasingly considered for biometric
arXiv:2605.19262v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely
arXiv:2410.18856v4 Announce Type: replace Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools c
i don't think i need cloud models anymore MTP speedup Qwen by 2.5x in Atomic Chat Dense vs MoE models on 2x RTX 5090 Qwen3.6 27B: 51 → 117 tps +137% Qwen3.6 35B-A3B: 218 → 267 tps +25% MTP drafts seve
arXiv:2603.24400v2 Announce Type: replace-cross Abstract: We propose a neural network model for contextual regression in which the regression model depends on contextual features that determine the ac
arXiv:2605.19227v1 Announce Type: cross Abstract: Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared par
arXiv:2605.18879v1 Announce Type: cross Abstract: Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web c
arXiv:2605.18667v1 Announce Type: new Abstract: Earth embedding models transform Earth observation data into embeddings uniquely tied to locations on the Earth's surface. These models are typically ev
arXiv:2508.06524v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly follow neural scaling laws that tie performance gains to rapidly expanding computational budgets, ra
arXiv:2602.12015v2 Announce Type: replace Abstract: Deploying large language models for clinical Text-to-SQL requires distinguishing two qualitatively different causes of output diversity: (i) input a
arXiv:2603.20216v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency
arXiv:2603.05308v2 Announce Type: replace-cross Abstract: Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language model
arXiv:2605.16445v1 Announce Type: cross Abstract: Masked Diffusion Language Models MDLMs replace autoregressive generation with iterative demasking and their privacy properties are largely unstudied.
arXiv:2605.16339v1 Announce Type: new Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference
arXiv:2605.18380v1 Announce Type: new Abstract: We introduce an extensive qualitative spatial and temporal reasoning (QSTR) benchmark for evaluating large language models (LLMs). We pose questions con
arXiv:2601.03425v2 Announce Type: replace-cross Abstract: Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumptio
arXiv:2605.18738v1 Announce Type: new Abstract: Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict, and such ethical dilemmas
arXiv:2605.18132v1 Announce Type: cross Abstract: Generative 3D models are deployed in gaming, robotics, and immersive creation, making source attribution critical: given a 3D asset, can we identify w
arXiv:2605.15725v1 Announce Type: cross Abstract: Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However
arXiv:2504.00289v3 Announce Type: replace-cross Abstract: The release of top-performing open-weight LLMs has cemented China's role as a leading force in AI development. Do these models support languag
arXiv:2605.15960v1 Announce Type: new Abstract: We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy sh
arXiv:2604.02812v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) have recently demonstrated strong capabilities in mapping multimodal observations to robot behaviors. However, most cu
arXiv:2605.15284v1 Announce Type: new Abstract: We introduce Tadpole, a novel foundation model for three-dimensional partial differential equations (PDEs) that addresses key challenges in transferabil
arXiv:2605.14709v1 Announce Type: new Abstract: Recent unified models integrate multimodal understanding and generation within a single framework. However, an 'understanding-generation gap' persists,
arXiv:2509.23023v3 Announce Type: replace Abstract: Large language models are increasingly deployed in multi-agent settings whose outcomes hinge on social intelligence, motivating evaluations of their
arXiv:2605.14809v1 Announce Type: new Abstract: Graph prompt tuning has shown great potential in graph learning by introducing trainable prompts to enhance the model performance in conventional single
arXiv:2508.17588v2 Announce Type: replace Abstract: Generation-driven world models create immersive virtual environments but suffer slow inference due to the iterative nature of diffusion models. Whil
Some models to try with Codex: kimi-k2.6:cloud (with vision support) glm-5.1:cloud If you don't yet have a paid subscription with Ollama's cloud, choose a model that supports reliable tool calling: ne
arXiv:2605.14090v1 Announce Type: cross Abstract: We put forth a critical theoretical framework for analyzing generative models both descriptively and normatively. Our thesis is that generative models
arXiv:2512.18951v3 Announce Type: replace Abstract: Infants learn not only object categories but also fine-grained visual attributes such as color, size, and texture from limited experience. Prior inf
arXiv:2605.13675v1 Announce Type: new Abstract: Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. Ho
arXiv:2509.19538v2 Announce Type: replace-cross Abstract: Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforceme
arXiv:2605.12516v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) often struggle to generate reliable responses in specialized engineering domains due to limited domain gr