Knowledge catalogue
arXiv:2502.07250v3 Announce Type: replace Abstract: Modern machine learning models excel at detecting individual actions, sounds, or scene attributes from short, localized observations. However, many
arXiv:2512.08897v2 Announce Type: replace Abstract: Content-aware layout generation is a critical task in graphic design automation, focused on creating visually appealing arrangements of elements tha
from internlm: We introduce Intern-S2-397B, our most capable multimodal foundation model for scientific intelligence and long-horizon agents. Intern-S2-397B scales along three critical dimensions: pre
I have a full model, it's ready to train. It's ~9b parameters. 9.4b to be more exact. That includes a 1/2/3 Engram table, Moonshot's AttnRes modeling, and RoPE / NoPE layering at 3:1 as more or less v
Looped transformers are a popular architecture topic right now. This new technical report extends the loop across tokens. Recurrent Looped Transformer (RLT) makes the decoder recurrent over every toke
arXiv:2609.11542v1 Announce Type: new Abstract: Large language model (LLM) training is among the fastest-growing sources of electricity demand in modern data centers, and power availability is a prima
arXiv:2609.11859v1 Announce Type: new Abstract: How does a language model's dependence on query-routing information and target knowledge change as it answers a question? We study this question through
The Coxon psyop was a decade and more than a billion dollars in the making. Here's the story. Coefficient Giving (formerly Open Philanthropy) is the grant-providing vehicle of Dustin Moskowitz. CG is
“We can’t slow down because China will beat us.” We can slow down. Chinese AI is waterskiing behind the US. Their AI capabilities come at a delay since they mainly come from distilling US AIs. If we s
arXiv:2609.10608v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in generative tasks across various areas, however their training process raises significant privacy
Anthropic: Most hypocritical company in history? 👉 Screams about how AI will kill everyone, while racing ahead. 👉 Moans about distillation while distilling the world’s books, articles, and other writi
arXiv:2609.11463v1 Announce Type: new Abstract: Segmenting bruises is a challenging task in medical imaging due to limited data and annotations, diffuse boundaries, and highly variable appearance. In
arXiv:2609.11495v1 Announce Type: new Abstract: Manchu, now critically endangered, was one of the principal languages of the Qing empire (1636-1912), and its extensive archival record is increasingly
arXiv:2609.10830v1 Announce Type: new Abstract: When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every p
arXiv:2609.11334v1 Announce Type: new Abstract: Natural Language Inference processes pairs of sentences to extract their semantic relations. NLI has been a hot research topic, integrated as a main com
arXiv:2609.11872v1 Announce Type: cross Abstract: Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes m
arXiv:2411.16975v2 Announce Type: replace Abstract: Hyperparameter tuning remains a significant challenge in the training of deep neural networks (DNNs), requiring manual search or time-intensive grid
arXiv:2609.11445v1 Announce Type: new Abstract: Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring
arXiv:2609.10756v1 Announce Type: new Abstract: Dense 3D depth perception fails under smoke, fog, and darkness because optical sensors cannot penetrate airborne particulates. mmWave radar remains usab
arXiv:2609.10917v1 Announce Type: new Abstract: Texture recognition remains challenging for modern vision models because discriminative evidence is often carried by higher-order spatial statistics rat
arXiv:2603.11298v3 Announce Type: replace Abstract: High dynamic range (HDR) novel view synthesis (NVS) aims to reconstruct HDR scenes from multi-exposure low dynamic range (LDR) images. Existing HDR
Hey gang, im wondering if you in theory could use ngrams as seen with Qwen 3.8 Flash or DS4.1 in order to dynamically train the model? Normally the ngram embeddings behave similar to a lookup table of
arXiv:2609.11804v1 Announce Type: new Abstract: Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this
arXiv:2609.10954v1 Announce Type: new Abstract: Continual world models must decide whether new data justify changing the model. Fixed replay schedules and prediction-error triggers specify when to upd
arXiv:2609.11842v1 Announce Type: new Abstract: Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kin
arXiv:2609.10811v1 Announce Type: new Abstract: We present 'overpainting', an image editing operation which offers both control over the location of the edit and awareness of the previous content in t
arXiv:2609.11648v1 Announce Type: new Abstract: Multivariate time series imputation (MTSI) aims to recover missing values in temporal data composed of multiple interdependent variables. This problem i
arXiv:2609.11722v1 Announce Type: new Abstract: The representation of 3D clothed humans as standardized 2D UV texture and displacement maps over an underlying body model has long been studied. This co
arXiv:2609.11079v1 Announce Type: new Abstract: Render--match--PnP relocalization establishes correspondences between query image pixels and 3D map points for camera pose recovery, but their potential
arXiv:2505.23942v2 Announce Type: replace Abstract: Prevailing activation functions such as Swish and GELU tend toward domain-specific optima, Swish was discovered via neural architecture search on vi
arXiv:2609.11752v1 Announce Type: cross Abstract: For industrial content risk control, the real deployment constraint is not average accuracy but how much risk can be auto-handled under high precision
arXiv:2609.11063v1 Announce Type: cross Abstract: Large language models learn similar behaviours, yet it remains unclear what structure they share or how to change one behaviour without disturbing oth
arXiv:2609.10947v1 Announce Type: cross Abstract: We propose the Platonic brain bridge hypothesis: omni models, which process video, audio and text jointly like the brain, converge on brain-like repre
arXiv:2609.09418v1 Announce Type: new Abstract: World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although
arXiv:2609.11375v1 Announce Type: new Abstract: Automated classification of sewer defects is essential for infrastructure condition assessment and maintenance decision-making, but existing deep learni
arXiv:2609.10643v1 Announce Type: new Abstract: Natural load-bearing patterns such as leaf venation, trabecular bone, and spider webs achieve high stiffness per unit mass, yet classical topology optim
arXiv:2609.07719v1 Announce Type: new Abstract: Medical imaging artificial intelligence (AI) is commonly developed as separate mappings from radiographs to diagnostic outputs or from clinical descript
arXiv:2609.10469v1 Announce Type: new Abstract: Automated plant disease diagnosis is increasingly deployed on farmer-held devices in regions where agronomic expertise is scarce and network connectivit
arXiv:2603.20957v4 Announce Type: replace-cross Abstract: Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely
arXiv:2609.10394v1 Announce Type: cross Abstract: Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the c
arXiv:2609.10317v1 Announce Type: new Abstract: Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite direction
arXiv:2609.09901v1 Announce Type: new Abstract: Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, b
arXiv:2609.09254v1 Announce Type: new Abstract: Field-programmable gate arrays (FPGAs) enable efficient neural-network inference, but most deployment flows either accelerate multiply-accumulate operat
arXiv:2511.18031v1 Announce Type: cross Abstract: Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is
arXiv:2609.08189v1 Announce Type: new Abstract: Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, how
arXiv:2609.09425v1 Announce Type: new Abstract: Educational data filters have become a practical way to improve language-model pre-training, but most filters treat educational value as a single scalar
// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear
arXiv:2609.10089v1 Announce Type: new Abstract: Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for near-term quantu
arXiv:2609.10292v1 Announce Type: new Abstract: Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandEra
Jacob was a senior researcher who joined Anthropic in May. My Anthropic colleagues and I had been trying to recruit him for ~2 years, because we knew he was a strong researcher at OpenAI. Before he le
arXiv:2609.10333v1 Announce Type: new Abstract: Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-fre
arXiv:2609.09572v1 Announce Type: cross Abstract: Synthetic data has become a promising way to scale model training beyond limited human-generated data but it may also induce strong model collapse (Do
arXiv:2609.09250v1 Announce Type: cross Abstract: A verifier for robot policies reads a candidate behavior and returns a score for how well it did, used both to evaluate vision-language-action policie
arXiv:2609.08390v1 Announce Type: cross Abstract: Full-duplex spoken dialogue systems enable simultaneous listening and speaking, but their audio-only perception often fails under background noise and
arXiv:2609.10540v1 Announce Type: new Abstract: Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanisms for maintaining persistent wo
arXiv:2609.10522v1 Announce Type: cross Abstract: Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains chal
arXiv:2609.09719v1 Announce Type: new Abstract: Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretra
arXiv:2609.10303v1 Announce Type: new Abstract: Face recognition (FR) is a widely used modality for biometric authentication, but conventional models rely on visible-spectrum imagery and degrade when
arXiv:2507.22076v2 Announce Type: replace Abstract: Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording
arXiv:2609.09925v1 Announce Type: cross Abstract: Modern vision-language-action (VLA) policies predict a whole chunk of actions: one to two seconds of coordinated motion emitted in a single forward pa