Knowledge catalogue
arXiv:2601.00282v2 Announce Type: replace-cross Abstract: Quantization is widely used to accelerate inference and streamline the deployment of large language models (LLMs), yet its effects on self-exp
arXiv:2608.24300v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outc
arXiv:2608.24039v1 Announce Type: cross Abstract: Manufacturing process planning transforms heterogeneous design information into coherent manufacturing decisions. However, existing approaches focus o
arXiv:2608.24048v1 Announce Type: cross Abstract: While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Exist
arXiv:2603.02041v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are predominantly trained on English-centric data, resulting in uneven performance for smaller languages. We stud
arXiv:2608.23961v1 Announce Type: cross Abstract: Background: Large Language Models (LLMs) have demonstrated strong performance across a variety of code-understanding tasks, leading many to believe th
Hi all, I'm looking for the best model for a hobby project and trying to make sense of the various data I came across. I know benchmarks do not often translate to the real world, especially to your pa
GLM-5.3-Flash by @Zai_org, aka Ox Alpha, is now live in LM Studio Bionic! This model surpasses GLM 5.2 in performance while being 9-10x cheaper. It also supports image input. In Bionic, this model is
GLM-5.3-Flash scores 57 on the Artificial Analysis Intelligence Index. At 0.09 Cost per Task, it sits comfortably on the Intelligence vs. Cost per Task Pareto frontier @Zai_org has released GLM-5.3-Fl
arXiv:2608.23870v1 Announce Type: new Abstract: When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks dependin
arXiv:2608.24121v1 Announce Type: new Abstract: Radiology report generation (RRG) has recently benefited from large language models, which substantially improve report fluency. However, clinically fai
arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge. The Model Context Protoco
arXiv:2608.23853v1 Announce Type: new Abstract: The interpretation of endoscopic imagery in ulcerative colitis is complex and subjective, with variability in human assessment and subtle mucosal inflam
Megathread for discussing the release of GLM-5.3-Flash. Quants Fine-Tunes & Abliterations Chat Templates Inference Server Support & Configuration Experiences, Benchmarks & Model Comparisons We'll try
Data preparation determines the ceiling of any supervised fine-tuning project. This first post in a two-part series covers the foundations of SFT data prep: quality checks, conversational (JSONL) form
arXiv:2608.24697v1 Announce Type: new Abstract: Predictive Coding (PC) is a neural learning paradigm that enables parallelizable neural network layer updates. However, the main bottleneck of PC Networ
arXiv:2608.23986v1 Announce Type: cross Abstract: Large language model providers are compute constrained, and their universal response to congestion is to degrade service: route queries to smaller mod
arXiv:2511.08873v3 Announce Type: replace Abstract: Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning me
arXiv:2608.24063v1 Announce Type: cross Abstract: While Vision Large Language Models (VLLMs) have achieved remarkable success in multimodal reasoning, their long-context inference remains prohibitivel
arXiv:2608.23978v1 Announce Type: new Abstract: Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a cen
arXiv:2512.13095v3 Announce Type: replace Abstract: To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into
AI storage infrastructure is becoming a more consequential planning issue as organizations move from model training toward agentic AI. As agents reason, act and reassess, they build longer contexts an
arXiv:2608.23283v1 Announce Type: new Abstract: General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information source
arXiv:2508.17527v2 Announce Type: replace Abstract: Accurately predicting travel mode choice is essential for effective transportation planning, yet traditional statistical and machine learning models
The reinforcement learning (RL) ecosystem is rapidly adopting Ray as the unified compute runtime for complex post-training workflows. Across Google Cloud, we see customers using Ray for workloads rang
arXiv:2608.21504v1 Announce Type: new Abstract: The rapid advancement of large language models (LLMs) has led to increasing interest in their application to scientific domains such as chemistry. Howev
arXiv:2608.23268v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning. Parameter-lev
arXiv:2608.21440v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have advanced end-to-end autonomous driving by leveraging foundation models for semantic reasoning and long-tail g
arXiv:2606.14782v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with lon
arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image i
arXiv:2608.21808v1 Announce Type: new Abstract: Multimodal Retrieval-Augmented Generation (RAG) with visual citation is crucial for ensuring the traceability and verifiability of MLLMs. However, curre
arXiv:2608.23029v1 Announce Type: new Abstract: Multi-agent debate can improve large language model reasoning by eliciting diverse hypotheses and critiques, yet its performance is often constrained by
For some reason I can only use Ollama through home wi-fi, everytime I try to use it while using my phone as a modem I get an error. Vpn doesn't help. Edit: problem fixed, works perfectly if VPN is in
arXiv:2606.14892v2 Announce Type: replace Abstract: An artificial intelligence must have a model of its environment that is causal, supporting reasoning about interventions and counterfactuals, and al
arXiv:2608.22467v1 Announce Type: new Abstract: Long-horizon language-model tasks --- multi-step reasoning and tool-using agents alike --- are limited by credit assignment. We analyze it through the p
arXiv:2508.14313v4 Announce Type: replace-cross Abstract: Test-time scaling strategies for Large Language Models predominantly rely on either reinforcement learning with sparse outcome rewards or sear
arXiv:2608.20492v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, post-training on large multi-task data
Graph: A cumulative metric of Speed x Context Size - the higher the dot - the better. Helpful for looking for the most balanced solution. The research relies on DFlash2 Q2 work by AnalogAlok: https://
arXiv:2608.20691v1 Announce Type: new Abstract: Panoramic image generation is increasingly important for immersive applications such as virtual reality, augmented reality, and 3D content creation. Unl
arXiv:2608.20686v1 Announce Type: new Abstract: Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints. Reinforcement learning (RL) offer
arXiv:2608.20382v1 Announce Type: new Abstract: We introduce a new architecture design for multimodal large language models (MLLMs), Libra, capable of both multimodal understanding and generation. Lib
Standard constrained RL assumes consequences are immediate and attributable to the current action. This breaks down whenever violations are delayed and stochastic, which is most real-world settings yo
arXiv:2608.21027v1 Announce Type: new Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents
arXiv:2608.20372v1 Announce Type: cross Abstract: The Federal Highway Administration (FHWA) mandates that over 600,000 bridges in the United States be evaluated against the Recording and Coding Guide
arXiv:2608.20366v1 Announce Type: cross Abstract: Molecular docking requires reasoning jointly about ligand pose and protein flexibility. Most diffusion-based docking models predict torsional updates
arXiv:2608.20743v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them
arXiv:2608.20362v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an answer
arXiv:2603.01493v2 Announce Type: replace-cross Abstract: Personal photo albums are not merely collections of static images but living, ecological archives defined by temporal continuity, social entan
Physical artificial intelligence is emerging as the next major phase of AI. These systems not only generate content or analyze data but also perceive, reason about and act in the physical world. The o
arXiv:2608.21098v1 Announce Type: new Abstract: Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or harm
arXiv:2608.20627v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves retrieval, reasoning, and answer generation across multiple hops. A retrieval error at hop 1
arXiv:2608.20516v1 Announce Type: new Abstract: Joint-embedding predictive architectures are selected almost universally by linear probing and effective rank. We report a case where both read healthil
WARNING: I think I made a mistake with omlx, and its results below seem to be without any kind of acceleration. I am rerunning them with Lightning MTP and ANE support for prefill. Will update the post
It performs at full capacity without any issues anywhere, but only the Ollama DeepSeek seems particularly trashy. Why on earth has the Ollama DeepSeek unusable trash that goes into over reasoning and
Hey guys, Inco AI shipped DFlash 2 a few days ago with a drafter for Qwen 3.8 27B and a llama.cpp PR. I built the PR and ran it against plain decoding, MTP, the n-gram lookup drafters, and my July DFl
One of the interesting properties we’ve observed around schema-guided, complex document extraction tasks 📑 is that coding agent harnesses are good baselines (in terms of cost/accuracy) for longer docu
This is the Qwen3.8-27B setup I actually use every day on one RTX 5090. I wanted to write it down with enough detail that another 5090 owner can reproduce it instead of guessing which memory knobs I u
arXiv:2608.19540v1 Announce Type: cross Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to
DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀 🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world know
arXiv:2608.20084v1 Announce Type: cross Abstract: Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasi