Search: “benchmark”

arXiv:2606.22550v1 Announce Type: new Abstract: Autoregressive visual models (AVMs) based on next-scale prediction have emerged as a prominent paradigm for image and video synthesis. However, decompos

arXiv:2606.22589v1 Announce Type: new Abstract: Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific ex

arXiv:2606.20852v1 Announce Type: new Abstract: Inference-time engineering can alter model behavior without fine-tuning. However, its utility for improving diagnostic performance in medical vision-lan

arXiv:2509.14641v2 Announce Type: replace Abstract: Dense 3D convolutions provide high accuracy for perception but are too computationally expensive for real-time robotic systems. Existing tri-plane m

arXiv:2606.13714v2 Announce Type: replace Abstract: Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent vi

arXiv:2606.19328v2 Announce Type: replace Abstract: Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward de

arXiv:2606.21223v1 Announce Type: new Abstract: Reliable localization is essential for intelligent transportation systems (ITS), including autonomous vehicles, quadruped last-mile carriers, and infras

arXiv:2606.22976v1 Announce Type: new Abstract: In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion model

arXiv:2606.20768v1 Announce Type: new Abstract: Visual anomaly detection is a fundamental task in industrial automation. While existing approaches have achieved notable progress in identifying structu

arXiv:2606.21661v1 Announce Type: new Abstract: Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist acros

arXiv:2606.21434v1 Announce Type: new Abstract: Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation learning. While RDL is evol

arXiv:2606.23503v1 Announce Type: new Abstract: Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfer to Earth Observation (EO), where

arXiv:2606.21287v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) enables robust transfer of knowledge from simulated to real environments while exploiting a subset of unlabeled tar

arXiv:2512.11061v2 Announce Type: replace Abstract: Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack in

arXiv:2602.08334v2 Announce Type: replace Abstract: Planning under uncertainty for real-world robotics tasks, such as autonomous driving, requires reasoning in enormous high-dimensional belief spaces,

arXiv:2606.23610v1 Announce Type: new Abstract: Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existin

arXiv:2606.20740v1 Announce Type: cross Abstract: Process Reward Models (PRMs) provide step-level verification for Large Language Model (LLM) reasoning, yet their training data acquisition remains a b

arXiv:2606.23543v1 Announce Type: cross Abstract: Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labe

arXiv:2606.20905v1 Announce Type: new Abstract: Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While spec

arXiv:2606.23327v1 Announce Type: new Abstract: Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-speci

arXiv:2606.22870v1 Announce Type: new Abstract: Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video understanding and reasoning capabilities of multimodal lar

arXiv:2606.17710v2 Announce Type: replace Abstract: Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That infe

arXiv:2606.23062v1 Announce Type: cross Abstract: We introduce VolHuMe, a dataset of high-quality 4D human scans captured with a state-of-the-art volumetric studio using 64 RGB and 32 depth cameras. V

arXiv:2606.23145v1 Announce Type: new Abstract: Operational event-detection systems are rarely assessed by pointwise accuracy alone. In anomaly detection, changepoint detection, and warning systems, t

arXiv:2606.22864v1 Announce Type: new Abstract: Hidden-state probing -- a linear classifier on a frozen vision-language model's internal activations -- has emerged as an attractive evaluation tool for

arXiv:2606.21641v1 Announce Type: new Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that 'warm-start' search from prior knowledge, proposing s

arXiv:2606.20724v1 Announce Type: cross Abstract: Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate

arXiv:2606.22079v1 Announce Type: cross Abstract: Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encoders for dense-terminology domains such as medicine,

arXiv:2606.22371v1 Announce Type: cross Abstract: Recent generative video compression methods leverage powerful generative priors to achieve perceptually pleasing reconstructions. However, most existi

In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the evaluation methodology we built on OpenStreetMap ground truth, four experiment

GLM-5.2 has been the most popular new model on Fireworks this past week. @ArtificialAnlys confirms why: #3 overall on GDPval-AA (1524 Elo), #1 open weights by 116 points. Interest is showing no signs

That's right, an open, MIT-licensed model beating GPT-5.5 (xhigh) on real-world agentic work! 🔥 Available for free on @huggingface for anyone to build on top off GLM-5.2 leads open weights models and

The largest LLM-as-a-Judge reliability audit yet. Researchers ran 21 judges from nine providers over roughly 541,000 judgments on MT-Bench, JudgeBench, and RewardBench. Findings: Validating a judge wi

>> Scalable Evaluation for AI Agents << If you run agent evaluation in production, this one is worth your time. It shows that front-loading human judgment into reusable evaluation assets is useful. Bu

We parsed this SpaceX equity research PDF faster than the time it took for Screen Studio to zoom in ⚡️🔥 liteparse is now the best open-source document parsing tool out there. There’s no reason to not

🚨🚨🚨A research project idea! How to measure world models? Everyone's talking about world models these days. World model here, world model there. We can argue about what 'world model' actually means, an

// Evolving Meta-Skill for Multi-Agent Systems // Can a multi-agent system get better at orchestration without touching a single weight? Automatic MAS generation has been stuck between two bad options

GLM 5.2 is a language model available through Ollama that has received positive user feedback for its performance capabilities. The post appears to be a social media testimonial praising the model's q

Hot take: GLM 5.2 might be the first open/public model that actually changes the enterprise AI cost equation. I played with it for a few hours today after friends told me to stop ignoring it. I expect

arXiv:2606.12320v1 Announce Type: new Abstract: Enterprise security was built to govern data boundaries: the protected surface was data at rest and in transit, and the controls -- access control, data

arXiv:2601.21817v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm.

arXiv:2505.13196v3 Announce Type: replace-cross Abstract: We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quart

arXiv:2606.11361v1 Announce Type: cross Abstract: Structured abstracts are important for biomedical literature processing, by facilitating information retrieval, text mining, and knowledge synthesis.

arXiv:2606.12337v1 Announce Type: cross Abstract: Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based opt

arXiv:2606.11219v1 Announce Type: cross Abstract: Audio language models (ALMs) are increasingly used for speech-based understanding, yet their ability to perform semantic reasoning beyond transcriptio

arXiv:2606.12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language.