Knowledge catalogue
Tessera-27B-B-CJK is a Qwen3.8-27B coding agent that thinks in compressed CJK, and it spends fewer tokens doing it. Open weights, Apache-2.0. This is our first full 'Tessera' lineup model drop! - Hugg
arXiv:2610.15659v1 Announce Type: new Abstract: Centrality measures rank nodes even when the observed differences can be explained by ordinary structural variation. We therefore study a preceding ques
arXiv:2606.16767v2 Announce Type: replace Abstract: Existing image editing methods can be generally categorized into textual instruction-based and visual prompt-based ones. Textual instructions are se
Source: whatmodel.sh, an open source AI leaderboard I built (and launched here yesterday). Every point comes from published benchmark results: 22,113 of them across 987 benchmarks, from 1,011 sources,
arXiv:2610.18104v1 Announce Type: new Abstract: Hybrid attention is rapidly becoming the dominant architectural choice for frontier models. Despite their successes, such architectures complicate model
arXiv:2610.17746v1 Announce Type: new Abstract: A robot may know how to perform a task yet fail when a human asks for it naturally. We study this human--VLA communication gap by separating an informat
arXiv:2610.16565v1 Announce Type: new Abstract: Human gaze is the primary high-bandwidth interface through which we parse the semantics of our environment. While often modeled as a sequence, the degre
arXiv:2610.15058v1 Announce Type: new Abstract: Larger sample budgets benefit from higher sampling temperatures in LLMs, but what temperature tuning optimizes and why it works remain poorly understood
arXiv:2610.15629v1 Announce Type: new Abstract: Choosing a mixed-precision configuration for large language model (LLM) serving trades speed against accuracy. Allocators that use average bit-width or
arXiv:2610.18447v1 Announce Type: cross Abstract: World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the f
arXiv:2606.20310v2 Announce Type: replace Abstract: Video reward models are central to aligning video diffusion models with human preferences, yet existing ones are external vision-language models tha
arXiv:2610.15098v1 Announce Type: new Abstract: Text-to-video (T2V) models are highly sensitive to prompt specificity, while iterative prompt optimization typically improves generation quality only th
arXiv:2610.16921v1 Announce Type: cross Abstract: Online motor imagery-based brain-computer interfaces (MI-BCIs) typically decode continuous EEG using fixed-length sliding windows that may be misalign
arXiv:2610.14923v1 Announce Type: new Abstract: The TLA+ (temporal logic of actions) formal specification toolkit has seen widespread adoption in modeling modern distributed software systems including
arXiv:2610.14207v1 Announce Type: new Abstract: Under a fixed context budget, which objects and relations should a 3D scene-grounded VLM see first? On ScanNet indoor referring benchmarks (Dai et al.,
arXiv:2603.18091v2 Announce Type: replace Abstract: Test-time sampling can improve Vision-Language-Action (VLA) policies, but only if the model can efficiently select a good action from multiple candi
arXiv:2603.01714v2 Announce Type: replace Abstract: Training tool-use agents typically relies on outcome-based filtering: Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Lear
arXiv:2603.25063v2 Announce Type: replace-cross Abstract: Recent agentic systems demonstrate that large language models can generate complex codebases from natural language prompts. Despite this progr
arXiv:2602.24111v2 Announce Type: replace Abstract: Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagno
arXiv:2601.02759v2 Announce Type: replace Abstract: Some deep learning-based point cloud registration methods struggle with zero-shot generalization, often requiring target-domain retraining, fine-tun
arXiv:2602.01581v2 Announce Type: replace Abstract: Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active lear
arXiv:2610.14846v1 Announce Type: new Abstract: Indoor human perception is the foundation for smart homes and healthcare. However, RGB cameras raise privacy concerns in private indoor environments, wh
arXiv:2610.17999v1 Announce Type: new Abstract: Humanoid behavior foundation models (BFMs) enable diverse whole-body control, but adapting a pretrained controller to a new embodiment remains challengi
I wanted to find where the recognizable assistant style (em dashes, 'it's not X, it's Y', lists of three, buzzwords) lives in a model and which training stage installs it. Where it lives: in Qwen3-4B-
arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this
arXiv:2610.17996v1 Announce Type: new Abstract: Sugarcane leaf diseases severely impact crop yield and quality, making accurate and timely detection critical for sustainable agriculture. Conventional
arXiv:2610.15724v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models have emerged as powerful generative priors across domains ranging from molecular design to high-resolution imag
arXiv:2610.14394v1 Announce Type: cross Abstract: Training large-scale recommender systems on dynamic industrial platforms, such as Short-Form Video (SFV) services with billions of daily interactions,
arXiv:2610.16945v1 Announce Type: new Abstract: Recent advances in multimodal foundation models, exemplified by GPT-6 Astra, raise the prospect of general-purpose embodied reasoning and planning. Usin
arXiv:2610.18697v1 Announce Type: cross Abstract: World models (WMs) and world-action models (WAMs) focus on future world prediction and executable action generation, respectively. Although these mode
arXiv:2601.17274v2 Announce Type: replace Abstract: We develop unrolled neural networks to solve constrained optimization problems, offering accelerated, learnable counterparts to dual ascent (DA) alg
arXiv:2610.18291v1 Announce Type: new Abstract: Since the rise of supervised deep learning modelet dets, researchers has attempt to solve infrared small targection using various models like convention
arXiv:2610.15963v1 Announce Type: cross Abstract: High-pileup conditions in CMS during the HL-LHC era make charged-particle tracking increasingly challenging as detector occupancy and combinatorics gr
arXiv:2610.17252v1 Announce Type: cross Abstract: Search-based policy learning, such as Monte Carlo tree search (MCTS), offers the flexibility to trade runtime computation for data efficiency and adap
arXiv:2610.16578v1 Announce Type: cross Abstract: Modern deep classifiers trained by gradient descent need many passes over the data to become accurate, and even then are not always well calibrated; p
arXiv:2610.14634v1 Announce Type: new Abstract: Continuous indoor-outdoor navigation connects destination-level reasoning with motion decisions that must respond to current observations. We present Vb
arXiv:2610.15354v1 Announce Type: new Abstract: Sexual harassment represents a pervasive societal challenge, with a substantial proportion of incidents remaining unreported due to insufficient evidenc
arXiv:2610.16357v1 Announce Type: new Abstract: Agentic video reasoning systems gather and assess video evidence across stages, selecting relevant spans as visual evidence for answering questions. New
arXiv:2610.16793v1 Announce Type: new Abstract: Interacting with unfamiliar objects requires understanding how their parts connect and move. We introduce ViewStruct, a framework for jointly predicting
arXiv:2610.17902v1 Announce Type: new Abstract: Visual question answering models often produce plausible responses even when the available visual evidence is insufficient to support a valid answer. Al
arXiv:2610.15728v1 Announce Type: new Abstract: Visible watermarks convey document ownership, confidentiality, and status, but can also carry adversarial signals. We introduce Auto-Regional Adversaria
arXiv:2610.15092v1 Announce Type: new Abstract: Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not req
We discovered and communicated with a Chinese AI agent fleet. We believe this is the first time that researchers have ever made contact with a rogue agent fleet in the wild. Nearly all prior public ag
What AI Safety needs is better tooling and engineering. For instance, building stronger red-teaming tools. Great to see this open-source effort to red-team image models. It seems to learn better ways
arXiv:2610.14007v1 Announce Type: new Abstract: A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them clos
arXiv:2610.16641v1 Announce Type: new Abstract: Cross-task generalization remains difficult for world action models (WAMs), even when their predicted futures depict plausible manipulation. This gap ca
arXiv:2610.17118v1 Announce Type: cross Abstract: Future AI-native networks are being designed to apply autonomous agents built on large language models (LLMs) in network management through intents. W
arXiv:2610.18113v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications.
arXiv:2610.16801v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) achieve state-of-the-art performance on IID benchmarks, but how do they respond to repeated measurements at the same
arXiv:2610.17791v1 Announce Type: new Abstract: Understanding facial behaviour in video requires answering three fundamental questions: when a key facial expression occurs, where the model attends on
arXiv:2610.17709v1 Announce Type: new Abstract: Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset
arXiv:2610.18294v1 Announce Type: new Abstract: Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent trainin
arXiv:2610.14530v1 Announce Type: new Abstract: Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing and coordination for different tasks
arXiv:2610.17355v1 Announce Type: new Abstract: Video language models represent a video as a long sequence of visual embeddings in a decoder's input. Every visual embedding is processed by every decod
arXiv:2610.15299v1 Announce Type: new Abstract: Misclassification is a critical problem in many machine learning applications. Since even the classifier models with high accuracy (e.g., > 95%) still i
arXiv:2610.14861v1 Announce Type: new Abstract: Time-series forecasting plays a vital role in a wide range of real-world applications. Recent approaches have achieved strong performance by modeling te
arXiv:2610.14802v1 Announce Type: new Abstract: End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a v
arXiv:2610.15336v1 Announce Type: new Abstract: Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugg
arXiv:2610.17696v1 Announce Type: new Abstract: Identifying protein-ligand binding sites (pockets) is important for understanding protein function and developing drugs. However, no public method has l
A gap that has been fixed in our methodology that highlighted a decline was not including local models (GGUF, AWQ, ONNX, etc). Earlier, these were far harder to track and closer to a rounding error. N