Jev's calibration was measured. The LLMs won [D]
Source: Jev Benchmarks Its training method is literally called 'Reinforcement Learning for Calibrated Decisions.' Calibration gap vs human labels (lower = better): Yes/no: Jev 5.0, Gemini 3.8 Flash 2.
Knowledge catalogue
Source: Jev Benchmarks Its training method is literally called 'Reinforcement Learning for Calibrated Decisions.' Calibration gap vs human labels (lower = better): Yes/no: Jev 5.0, Gemini 3.8 Flash 2.
arXiv:2609.21381v1 Announce Type: cross Abstract: We investigate whether coupling a time-series foundation model to hydraulic project knowledge improves surrogate forecasting of HEC-RAS water-surface
arXiv:2603.29532v2 Announce Type: replace-cross Abstract: The Linear Parameter-Varying (LPV) framework enables the construction of surrogate models of complex nonlinear and high-dimensional systems, f
arXiv:2609.21945v1 Announce Type: new Abstract: Urban transportation networks present complex optimization challenges spanning calibration of high-fidelity simulators and real-time operational control
arXiv:2609.21325v1 Announce Type: new Abstract: Agentic marketplaces are emerging where AI agents with varying capabilities autonomously complete specialized tasks for buyers. A major challenge of suc
arXiv:2609.21061v1 Announce Type: new Abstract: Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce
been working on this thing called OpenComms for a bit. basically i keep multiple coding agents open at once, usually stuff like a lead, builder, reviewer etc, and i got sick of copying messages betwee
arXiv:2609.21026v1 Announce Type: new Abstract: Localizing a radio-frequency (RF) transmitter from received signals often requires a model of the environment to predict how obstacles block and reflect
Hey everyone! It has been quite a while since the last SupraLabs model - but today we've something special for y'all: Supra2-IMG It's a 100M parameter DiT text-to-image model trained entirely from scr
Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepS
arXiv:2602.16313v2 Announce Type: replace Abstract: Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by
Since there’s no comparison chart on the model page, I asked Perplexity to compare it against some relatively small open-weight models in a similar size range. Here are the results. Upd. Terminal-Benc
MiMo-V2.6-Pro debuts as the top open weights model on the Artificial Analysis Intelligence Index (46). At 0.13 per Intelligence Index task, it lands on the Intelligence vs. Cost per Task Pareto fronti
Carl Franzen / VentureBeat: MiMo-V2.6-Pro ties Grok 4.7 (xHigh) and beats GLM-5.3 (max) on Artificial Analysis' Intelligence Index, making it the benchmark's top-scoring open-weight model — That puts
Sorry for the pretentious name, I know, I know.. It just contains all the pieces I would like to see a AGI model to have, and I can't stand the temptation. Before throwing rocks at me, please take a g
arXiv:2609.20850v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easil
arXiv:2609.20945v1 Announce Type: new Abstract: Undesired information such as harmful content and private data propagates through Multilingual Large Language Models (LLMs) via direct training and indi
arXiv:2609.21288v1 Announce Type: new Abstract: Surface electromyography (sEMG)-based silent speech interfaces are limited by cross-user variability and calibration burden. We study a limited-data set
My buddy only knew Gemini when it came to AI. Today I set up Hermes Agent for him, and he's literally calling me every half hour, totally blown away and calling me the modern-day Tesla. He got more do
arXiv:2603.27884v2 Announce Type: replace Abstract: We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under f
arXiv:2609.21870v1 Announce Type: cross Abstract: Modern deep learning models achieve impressive generalization through over-parameterization, but this paradigm often struggles with overfitting and me
arXiv:2609.21707v1 Announce Type: new Abstract: We present NeuRIO, a streaming neural estimator for anchor-free 6-DoF relative inertial odometry using only identified inter-robot bearings, ranges, and
arXiv:2603.29715v2 Announce Type: replace Abstract: Nonnegative matrix factorization (NMF) approximates a nonnegative matrix, X, by the product of two nonnegative factors, WH, where W has r columns an
arXiv:2609.21179v1 Announce Type: new Abstract: Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors
Every AI factory needs power and cooling that fit its computing architecture. As AI infrastructure expands, power, cooling, water, site and grid constraints are shaping what builders can deploy. Choos
arXiv:2609.21822v1 Announce Type: new Abstract: While object detection has advanced through improved architectures and open-vocabulary models, we provide strong evidence that benchmark quality is limi
arXiv:2609.21392v1 Announce Type: new Abstract: Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather
arXiv:2609.22069v1 Announce Type: new Abstract: Reference-to-video (R2V) generation is evolving toward increasingly general and versatile reference control, giving rise to the emerging paradigm of omn
arXiv:2609.21465v1 Announce Type: cross Abstract: We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly
arXiv:2609.21626v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized different
I'm one of the maintainers of SurfSense, so this is self-promotion. I'm posting here because the model-picking part is what I think this sub will have opinions on, and I want real feedback more than u
arXiv:2609.21527v1 Announce Type: new Abstract: Graph-enhanced multi-agent systems (G-MAS) coordinate large language model agents through communication graphs and role assignments, which determine how
arXiv:2609.21178v1 Announce Type: new Abstract: Service applications for human-robot interaction are commonly written against the hardware-specific interfaces of one platform, so a change of hardware
arXiv:2609.22053v1 Announce Type: new Abstract: Graph Convolutional Networks (GCNs) are highly sensitive to label noise, since corrupted supervision can propagate through the graph and degrade learned
arXiv:2609.20836v1 Announce Type: new Abstract: Physiological signals support diverse clinical and monitoring tasks, yet existing physiological signal foundation models typically require task-specific
arXiv:2609.21263v1 Announce Type: new Abstract: Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimi
arXiv:2609.21493v1 Announce Type: new Abstract: Multimodal large language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whet
arXiv:2609.21838v1 Announce Type: new Abstract: Social-navigation algorithms are often evaluated under a fixed pedestrian-behavior distribution, despite substantial variation in pedestrian responses t
arXiv:2609.22040v1 Announce Type: new Abstract: Current Vision-Language-Action (VLA) models for autonomous driving operate primarily through feedforward inference across the perception--reasoning--pla
arXiv:2609.21673v1 Announce Type: new Abstract: Probabilistic Graphical Models (PGMs), especially Bayesian Networks (BNs), expose directed structure and probabilistic parameters, making them natural s
If anyone is interested in using Ollama with the Prism-ML model prism-ml/Bonsai-27B-gguf · Hugging Face I setup a repo with an install script that patches Ollama and pulls the Prism-LM llama.cpp code
arXiv:2609.21264v1 Announce Type: cross Abstract: Spatial NPUs such as AMD XDNA place compute tiles beside small local memories and leave data movement between them to software. Mapping a multi-stage
arXiv:2609.21369v1 Announce Type: cross Abstract: This paper presents a comprehensive framework for robot manipulation failure analysis that includes binary failure detection, failure categorization,
arXiv:2609.21541v1 Announce Type: new Abstract: Multi-label few-shot learning (MLFSL) remains a significant challenge in medical image analysis (MIA). Current metric-based meta-learning methods face t
Small, free finding. I use local Qwen models for typed decisions: a state plus a question with fixed allowed answers, and I read the probability of each answer from the logits of one forward pass inst
arXiv:2609.22038v1 Announce Type: new Abstract: We introduce QuranicMMLU, a benchmark for evaluating generative AI on Quranic Arabic across multiple dimensions of linguistic complexity. Existing Quran
Qwen-Image-2.1 × @HuggingApps: live demo on Spaces! 🖼 One single checkpoint for generation and editing. Try it in your browser, no setup needed. 👇 Qwen Image 2.1 is here! 🖼️ A 7B params native image g
arXiv:2609.20847v1 Announce Type: new Abstract: Anxiety is among the most common mental health conditions, and people often write about it online well before seeking clinical help. Practitioners build
arXiv:2609.20845v1 Announce Type: new Abstract: A decoder that turns video or audio into text conventionally consumes the entire input before emitting a word. Offline this is merely more than the task
arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Rea
arXiv:2609.21522v1 Announce Type: new Abstract: Recent pre-trained foundation models provide rich multi-modal priors for downstream 3D vision tasks. However, the effectiveness of these representations
arXiv:2609.21108v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has achieved strong performance across a wide range of continuous-control problems. These continuous-control policies,
arXiv:2609.21197v1 Announce Type: new Abstract: Sparse longitudinal CT follow-up limits lesion-size forecasting when only a few prior observations are available. We constructed a five-visit DLT-derive
arXiv:2609.21663v1 Announce Type: new Abstract: Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats every lexical deviation from the reference as equall
arXiv:2609.20830v1 Announce Type: new Abstract: Revision-capable generation is appealing because it can insert or revise earlier content, but many non-autoregressive and edit-based approaches obtain t
arXiv:2609.21371v1 Announce Type: new Abstract: Social Proactive Intelligence (SPI) extends proactive assistance beyond task completeness to consider social appropriateness in diverse embodied scenari
arXiv:2609.21186v1 Announce Type: cross Abstract: Accurate initialization is essential for reliable visual-inertial odometry (VIO), but it is often ill-conditioned under degenerate motions. Existing m
arXiv:2609.21223v1 Announce Type: new Abstract: Vision-language-conditioned robot policies integrate perception, language understanding, and control for general-purpose manipulation. However, existing
arXiv:2609.21242v1 Announce Type: new Abstract: Reference-guided diffusion stylization aims to transfer visual style from a reference image while preserving the semantics specified by a text prompt. H
arXiv:2609.21740v1 Announce Type: new Abstract: Latent world models enable planning by predicting the effects of actions in a learned representation space, but their predictions can become unreliable