Knowledge catalogue
arXiv:2609.04590v1 Announce Type: cross Abstract: Catheterisation image processing requires segmentation models that are fast, accurate and explainable. While most of the existing studies usually focu
arXiv:2609.04239v1 Announce Type: new Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series (TS) foundation model (TSFM) tailored to financial
arXiv:2609.04494v1 Announce Type: cross Abstract: We present Hakken, a domain-agnostic prediction and explanation system performing knowledge prediction, i.e., growing scientific knowledge by establis
arXiv:2609.04298v1 Announce Type: new Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We
arXiv:2609.04444v1 Announce Type: new Abstract: Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put a price on avoiding the side ef
The missing control is visible in sudoingX’s Ling-3.0-flash benchmark graphics. The earlier table leaves Ling’s no-speculation baseline as “not measured.” The later code/prose graphic fills it in: abo
arXiv:2609.05309v1 Announce Type: cross Abstract: Hyper-Connections and their manifold-constrained variant mHC widen a residual pathway from one stream to n, yet how trained models use this capacity r
arXiv:2609.04797v1 Announce Type: new Abstract: Deep models for sales forecasting, such as WaveNet-style dilated convolutional networks, are accurate but opaque: when a single model predicts sales for
Jensen Huang says that AGI has been achieved. I strongly disagree. GPT-6 performs really well on benchmarks, including ARC-AGI-3. But benchmark performance is not the same as general intelligence. GPT
arXiv:2609.04283v1 Announce Type: new Abstract: Aligning video generative models to human preferences heavily relies on Reinforcement Learning (RL), which suffers from extensive computational overhead
arXiv:2609.04939v1 Announce Type: new Abstract: The visual aesthetics of photographs are deeply influenced by lens characteristics such as aperture shape, optical vignetting and optical diffraction, w
arXiv:2609.04250v1 Announce Type: cross Abstract: An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken
arXiv:2609.04598v1 Announce Type: cross Abstract: We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language
arXiv:2609.04263v1 Announce Type: cross Abstract: Low-bit key--value (KV) caches reduce the memory required for autoregressive decoding, but the resulting quality loss depends on the model and quantiz
arXiv:2609.04808v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found i
arXiv:2609.05141v1 Announce Type: new Abstract: Scientific papers require models to reason jointly over text, equations, figures, tables, code, and datasets while preserving the provenance of supporti
arXiv:2609.05125v1 Announce Type: new Abstract: Evaluating the calibration of Large Language Models (LLMs) is critical for their safe deployment as zero-shot classifiers. Yet, commercial API providers
arXiv:2603.21309v4 Announce Type: replace Abstract: Facial expression recognition (FER) in videos requires model personalization to capture considerable variation across subjects. Vision-language mode
arXiv:2609.05117v1 Announce Type: cross Abstract: Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We i
I recently ported VDN-H3 (Video DeltaNet for MiniMax H3) to Vpipe and tested it on an M5 Pro 24GB. The benefit scales with both sequence length and resolution: at 832×480, VDN-H3 starts to pull ahead
arXiv:2609.04827v1 Announce Type: new Abstract: Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, t
arXiv:2609.04384v1 Announce Type: cross Abstract: Chinese online comments often convey social meaning through indirect and playful language that is hard to interpret without context. Existing evaluati
I'm using DS-V4-Flash-Vision with Q8_K_XL quantization locally as my everyday engine, and for some time now I've been doing a lot of comparisons with Qwen3.8-Flash-Next, also with Q8_K_XL quantization
Excellent analysis, and yes this happens every single time. (Tyler Cowen said o3 was AGI!) Every time a new model drops, GPT, Claude, Gemini, Grok, DeepSeek, somebody on this app declares that we have
I released this today because I was 100% sure a frontier AI would figure it out Matter is chiral => the first derivation of the standard model & three generations uniquely That’s all, nothing else Can
Anyone who has a 3D printer and get use of it finds it incredibly useful for those odd jobs around the house, a missing bracket, a cable router, steam deck holder and so on. In the past if I was missi
Otaku is an LLM frontend, primarily designed for roleplay, an alternative to SillyTavern and the like. However, It also works for general-purpose chat with local backends (including Ollama) or cloud m
First, I'd like to thank the Qwen and Unsloth teams for the Qwen3.8 27b UD Q4_K_XL. Fits the poor 24GB of 3090 VRAM with 100k context at Q8 and works phenomenally well! Imho if theres anything that ca
arXiv:2602.23996v2 Announce Type: replace Abstract: Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attenti
Anthropic’s planned initial public offering, potentially valuing the company at up to $2 trillion, will be examined under a novel governance model that places an external Long‑Term Benefit Trust (LTBT
arXiv:2509.14435v3 Announce Type: replace Abstract: Large language models (LLMs) have transformed natural language processing (NLP), enabling diverse applications by integrating large-scale pre-traine
arXiv:2609.03807v1 Announce Type: cross Abstract: A free pause token gives a language model extra compute to form each next-token prediction (as a pause, or thinking, token does) but carries that comp
After Qwen3.8 27B came out, I decided to benchmark the models that could fit in my GPU (RTX 5080) on my actual code (C code), the results were not completely unexpected but some quants were definitely
arXiv:2609.03181v1 Announce Type: new Abstract: We present Jina-OCR-v1, an end-to-end document parsing model built to serve on low-budget GPUs. It combines the compressed-vision encoder and the 3B mix
arXiv:2606.20954v2 Announce Type: replace-cross Abstract: Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an e
arXiv:2609.03511v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate strong multilingual reasoning performance, yet their robustness to semantics-preserving structural variation re
arXiv:2609.03261v1 Announce Type: cross Abstract: A benchmark score credits final answers, but not the route by which an item can be answered. In medical multimodal multiple-choice questions (MCQs), t
arXiv:2609.03026v1 Announce Type: cross Abstract: Mechanistic interpretability is increasingly used to guide interventions such as activation steering, circuit removal, and safety monitoring. Yet an i
arXiv:2609.03104v1 Announce Type: cross Abstract: Conformal risk control is an emerging framework for the safe deployment of machine learning models with finite-sample guarantees. To accommodate a bro
Here we go again... Discovery of a new OpenAI agent message board by Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, and Thomas Larsen describes the latest accidental cyberattack by models being tra
arXiv:2609.03450v1 Announce Type: cross Abstract: An agent that inherits six one-line memories may pull at most one archived source record before acting; a directive written into the store can steer t
arXiv:2609.02947v1 Announce Type: cross Abstract: Significant challenges remain in AI-driven educational systems in balancing privacy preservation with accurate cognitive diagnosis. To overcome this,
arXiv:2609.03430v1 Announce Type: new Abstract: Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memor
arXiv:2609.03142v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies fuse multimodal sensory inputs, but training on limited and homogeneous robot demonstrations encourages spurious
arXiv:2609.03981v1 Announce Type: new Abstract: Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue, so that analysis tools built for health
arXiv:2609.03813v1 Announce Type: new Abstract: Real-world image super-resolution (SR) increasingly relies on Diffusion Transformer (DiT) backbones, whose internal activations can be dominated by a sm
arXiv:2609.03874v1 Announce Type: new Abstract: Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs
arXiv:2609.03806v1 Announce Type: new Abstract: Scalable Vector Graphics (SVG) generation is attracting increasing attention as generative models improve in expressiveness and controllability. Progres
arXiv:2609.03395v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong performance on table question answering, yet their accuracy often degrades as table size increases. We
arXiv:2609.03652v1 Announce Type: new Abstract: Synthetic data augmentation has become a common strategy for addressing class imbalance in NLP, but most approaches focus on the quantity and diversity
I got access to GPT-6 Astra this afternoon, so naturally I used it to generate SVGs of pelicans riding bicycles - at low, medium, high, xhigh and max reasoning levels (Astra doesn't support reasoning=
arXiv:2606.18338v2 Announce Type: replace Abstract: The search for life beyond Earth will depend on detecting faint signatures in the atmospheres of potentially habitable exoplanets. Interpreting thos
arXiv:2609.02990v1 Announce Type: cross Abstract: To scale up collective decision-making, participatory democracy platforms such as Polis and Remesh enable online deliberation among thousands of parti
Github link: https://github.com/thatblend/LLMPSP I wanted to see what the PSP can theoretically handle and I got my answer - a 90M model is about the max it can do without atrocious inference speeds.
arXiv:2609.02253v1 Announce Type: new Abstract: Deep research agents augment large language models with external tools to answer complex, long-horizon questions through multi-turn reasoning. Learning
model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading G1/G2 infrastructure for variable-per-l
arXiv:2609.02831v1 Announce Type: new Abstract: Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restora
arXiv:2602.22453v3 Announce Type: replace Abstract: Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the
arXiv:2609.02131v1 Announce Type: cross Abstract: Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a b
arXiv:2609.02730v1 Announce Type: new Abstract: Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user beh