Knowledge catalogue
arXiv:2608.11361v1 Announce Type: cross Abstract: Tokenizer vocabulary size is a foundational design choice in large language model (LLM) infrastructure, yet it is typically fixed at training time bas
arXiv:2608.11745v1 Announce Type: new Abstract: Pose-driven human animation synthesizes a video of a target person from a single reference image and a driving pose stream. Real-time generation is esse
Release: llm-gemini 0.33 It's been a while since the last llm-gemini release. This version of the plugin adds support for today's Gemini 3.7 Flash release, plus gemini-3.6-flash, gemini-3.5-flash-lite
arXiv:2508.12450v2 Announce Type: replace Abstract: This article presents an adaptive mean shift algorithm in which every parameter used at a point is derived from that point's own distance distributi
arXiv:2608.11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that
arXiv:2608.12045v1 Announce Type: new Abstract: Despite growing interest in weakly supervised video anomaly detection (WSVAD), current methods struggle to bridge the gap between coarse temporal superv
arXiv:2608.11822v1 Announce Type: new Abstract: A growing body of work reports that language models represent task-relevant latent structure that they fail to use. Whether such structure, once located
arXiv:2608.11735v1 Announce Type: cross Abstract: Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity. Pr
arXiv:2608.11327v1 Announce Type: new Abstract: Specialist training beats generalist scale when forecasting financial statements. To our knowledge, no prior work jointly forecasts complete financial s
arXiv:2510.26690v3 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a popular technique for parameter-efficient fine-tuning of large language models (LLMs). In many real-world sc
arXiv:2608.11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instruction
Alex Townsend: Mathematicians say a neurosurgery resident used ChatGPT, powered by GPT-5.6, to solve Crouzeix's conjecture, a major open problem in numerical linear algebra — On July 30, 2026, the fir
arXiv:2608.11616v1 Announce Type: new Abstract: Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to
arXiv:2608.11566v1 Announce Type: cross Abstract: Browser-based webcam gaze trackers are increasingly used for crowd-scale data collection and in clinical settings where lab eye trackers are impractic
arXiv:2608.12036v1 Announce Type: new Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain p
arXiv:2511.01143v2 Announce Type: replace-cross Abstract: Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored
The maximum frame count allowed by the native 'MiniMax H3 Reference to Video' node technically is 1008, even if that's way over the training range of the model, which is 324 frames. But why not try? S
arXiv:2608.11749v1 Announce Type: cross Abstract: Multi-objective optimization (MOO) has demonstrated significant success in multi-task learning by mitigating task conflicts through gradient manipulat
arXiv:2608.11655v1 Announce Type: cross Abstract: Motion-centric video reasoning is fundamental to interactive applications such as robotic manipulation and autonomous navigation. However, multimodal
arXiv:2608.11755v1 Announce Type: cross Abstract: Long-form song generation models continue to improve in duration, structural integrity, and acoustic complexity, making reliable aesthetic rewards inc
My @aiDotEngineer talk on lessons learnt from studying memory systems for a year: > the evolution of chatgpt and claude memory over the years > their architectural convergence > why memory cannot be o
My cofounder Tim, whom you will not find on X, shares some of the strategic thinking behind our latest updates https://venturebeat.com/infrastructure/mistral-ai-wants-to-build-1-gigawatt-of-european-c
arXiv:2608.12197v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in circuit design workflows, yet their reliability on simulator-facing SPICE netlist recognition an
arXiv:2608.11352v1 Announce Type: new Abstract: Sign language translation has achieved strong results with Transformer architectures, yet recent improvements largely rely on scaling model capacity at
arXiv:2608.11941v1 Announce Type: new Abstract: We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conje
Frederic Lardinois / The New Stack: OpenAI launches Computer History, an opt-in feature that turns recent computer activity on macOS into memories and a timeline that ChatGPT and Codex can use — OpenA
Zac Hall / 9to5Mac: OpenAI previews Ultrafast, an API tier powered by Cerebras that runs GPT-5.6 Sol up to 14× faster and generates up to 750 output tokens per second — OpenAI is previewing a new way
arXiv:2512.07826v3 Announce Type: replace Abstract: The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instru
arXiv:2608.11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cro
Our most intelligent workhorse model yet for coding and agents has arrived ⚡ Meet Gemini 3.7 Flash. — Crush that seemingly endless to-do list. Gemini Spark in the @geminiapp now uses 3.7 Flash. The ne
out of curiosity, i tasked fable to figure this thing out and it looks like the 'saas killer' is done. ▲ it maxed out Fable 5 + used most of Codex limits ▲ most of the work was done within 45h session
arXiv:2506.17332v2 Announce Type: replace-cross Abstract: By 2050, people aged 65 and over are projected to make up 16% of the global population. As aging is closely associated with increased fall ris
arXiv:2608.11465v1 Announce Type: cross Abstract: PAC-Bayes theory provides generalization guarantees by controlling the Kullback--Leibler (KL) divergence between posterior and prior distributions ove
arXiv:2509.18751v4 Announce Type: replace Abstract: Recently reconstruction-based deep models have been widely used for time series anomaly detection, but as their capacity and generalization capabili
arXiv:2608.11282v1 Announce Type: cross Abstract: Quantifying myocardial perfusion from cardiac magnetic resonance (CMR) can be achieved by fitting tracer-kinetic models to the dynamic contrast-enhanc
arXiv:2608.11215v1 Announce Type: new Abstract: Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase
Powered by @Cerebras, Ultrafast generates up to 750 tokens per second, bringing our most intelligent model to products and workflows where every second counts. Ultrafast is designed for businesses whe
On Aug 13 2026, OpenAI announced a preview of its “Ultrafast” mode for the GPT‑5.6 model, called Sol, which claims inference speeds up to 14× faster than current releases. The feature is initially rol
arXiv:2505.03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-triv
Reducing Retrieval and Calls When a retrieval-augmented generation (RAG) agent runs, it often has to plan a search, check the evidence it gets back, and try again when that evidence falls short. Those
arXiv:2608.11329v1 Announce Type: cross Abstract: A common approach to adding audio to a vision-language model is to train or adapt a large omni-modal system. We show that a lightweight alternative ca
https://preview.redd.it/nqr9nj5028jh1.png?width=1516&format=png&auto=webp&s=47af40a0737429dc65f2e455b87b2db81725cb14 So I wanted to see... is it possible/viable to run this perhaps once in a while som
arXiv:2608.12004v1 Announce Type: cross Abstract: In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, T
arXiv:2608.11572v1 Announce Type: new Abstract: Coarse-grid numerical solvers can substantially reduce the computational cost of time-dependent PDE simulation, but under-resolution often degrades both
arXiv:2608.11241v1 Announce Type: new Abstract: Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: genera
arXiv:2607.16261v2 Announce Type: replace-cross Abstract: Modern optimizers combine gradients from the current mini-batch with historical optimization state, such as momentum or adaptive moments. Whil
arXiv:2608.11239v1 Announce Type: cross Abstract: Administering Database Management Systems (DBMS) instances requires Database Administrators (DBA) to balance performance in terms of Service Level Agr
arXiv:2510.17543v3 Announce Type: replace Abstract: Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging. We study edge-cloud casc
arXiv:2603.11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams. While pre-trained models
arXiv:2608.11564v1 Announce Type: new Abstract: Depth estimation from thermal images is highly valuable for robotic applications in adverse conditions, such as nighttime and rainy weather. Recent stud
arXiv:2608.11233v1 Announce Type: cross Abstract: A dense, pretrained language model can be retrofitted with recurrent depth and learn an iterative latent transition that persists after outcome-only a
arXiv:2608.11977v1 Announce Type: new Abstract: Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, per
arXiv:2411.15122v2 Announce Type: replace-cross Abstract: AI-driven models have demonstrated significant potential in automating radiology report generation for chest X-rays. However, there is no stan
arXiv:2608.11580v1 Announce Type: cross Abstract: Autonomous driving simulation requires diverse and scalable lane-level HD maps to support long-horizon evaluation across complex road networks. Existi
arXiv:2603.24060v3 Announce Type: replace Abstract: Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environm
arXiv:2608.11704v1 Announce Type: cross Abstract: Dynamic Time Warping (DTW)-based Nearest-Neighbor (NN) classifiers are effective for time-series classification but are vulnerable to mislabeled train
arXiv:2608.11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks wit
arXiv:2608.12129v1 Announce Type: new Abstract: While retrieval-augmented generation (RAG) has proven effective at giving LLMs access to external knowledge, mainstream dense-retrieval implementations
arXiv:2608.12127v1 Announce Type: new Abstract: Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is
arXiv:2608.11285v1 Announce Type: cross Abstract: Despite the practical relevance of sparse decision-based black-box threats, they have received limited attention in semantic segmentation. To bridge t