Knowledge catalogue
arXiv:2608.09816v1 Announce Type: new Abstract: Zero-shot object-goal navigation (ZSON) requires a robot to find a named object category in a building it has never entered. The prevailing approach sco
arXiv:2608.08485v1 Announce Type: new Abstract: Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inf
I wanted to find out whether a huge text-only MoE could be given basic vision without retraining the language model itself. The short answer is yes. I froze DeepSeek V4 Flash and a 417M-parameter Moon
arXiv:2608.09779v1 Announce Type: cross Abstract: Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly
Needs a lot of requests compared to Qwen (almost twice) and Gemma (almost x3). Final score is fine, even though it is 'not a coding model' https://wonderrico.github.io/local_llm_benchmark/benchmark-ma
arXiv:2512.01045v2 Announce Type: replace Abstract: Data-intensive artificial intelligence applications increasingly rely on large-scale, high-quality, explainable, and reproducible datasets, yet the
arXiv:2608.09121v1 Announce Type: new Abstract: Web navigation agents are capable of addressing various types of tasks on different websites. Current baselines on web navigation are either unimodal or
GitHub: https://github.com/xmarre/ComfyUI-DoRA-Dynamic-LoRA-Loader Release v1.0.39: https://github.com/xmarre/ComfyUI-DoRA-Dynamic-LoRA-Loader/releases/tag/v1.0.39 Also available through ComfyUI Manag
arXiv:2608.09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement,
arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each spar
arXiv:2505.19766v4 Announce Type: replace Abstract: Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet exi
arXiv:2608.08830v1 Announce Type: new Abstract: Legal Statute Prediction (LSP) involves automatically identifying relevant legal statutes given factual descriptions in legal documents, typically frame
AI-powered tax compliance has to meet a standard that many artificial intelligence applications don’t: The answers must be exactly right. While large language models can generate unpredictable results
arXiv:2506.07223v2 Announce Type: replace Abstract: Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safe
arXiv:2608.08612v1 Announce Type: cross Abstract: Recently, retrieval-augmented and memory-augmented methods have emerged as two promising paradigms for long-video question answering. However, existin
arXiv:2608.09410v1 Announce Type: new Abstract: Modern vision-language-action (VLA) policies have acquired broad manipulation skills, but typically generate each action chunk from the current observat
arXiv:2608.09278v1 Announce Type: cross Abstract: GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity
I'm guessing that many people have been waiting for this comparison. For clarity, both models are running at full FP16 KV-cache. Due to VRAM limitations, Muse Glimmer is running full 262,144 context,
arXiv:2608.08219v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Traditional deep learn
We converted the model from the original safetensors and found two issues. The first one made our quantization fail several times, the second one does not fail at all, it just quietly ruins the base 1
I don’t even care anymore whether these posts are *actually* AI-generated. The problem is that there’s now a very specific style of internet writing that instantly makes my brain refuse to continue re
arXiv:2608.06773v1 Announce Type: new Abstract: Visual object tracking aims to continuously locate specific targets within sequential frames, evolving from single-modal methods to multi-modal ones. Ho
arXiv:2608.06729v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially ob
arXiv:2608.06609v1 Announce Type: new Abstract: Automated item evaluation (AIE) refers to the use of computational methods to assess item quality without requiring manual expert review or field testin
arXiv:2608.07434v1 Announce Type: new Abstract: Event boundaries in continuous video are ambiguous: re-annotate the same query-video pair and independent annotators mark moments that overlap by less t
arXiv:2604.25220v2 Announce Type: replace Abstract: Data videos combine animated visualizations with synchronized narration to communicate quantitative information and are widely used in journalism, e
arXiv:2608.07147v1 Announce Type: new Abstract: Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from co
arXiv:2608.07196v1 Announce Type: new Abstract: Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system
arXiv:2608.06876v1 Announce Type: cross Abstract: In the era of Industrial Internet of Things (IIoT) and Cyber-Physical Systems (CPS), Federated Learning (FL) offers a promising decentralized intellig
arXiv:2608.07213v1 Announce Type: new Abstract: Test-time scaling can correct difficult text-to-SQL queries, but the extra computation is normally discarded after each answer. Systems increasingly ret
arXiv:2608.07282v1 Announce Type: new Abstract: The recent advances in neural language models have also spurred much work in computational psycholinguistics, asking whether neural LMs are also promisi
arXiv:2608.06836v1 Announce Type: new Abstract: We study the problem of inserting new furniture into indoor scene images. Under masked single-view 2D image-plane conditioning, however, the physical sc
arXiv:2603.27435v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models a
arXiv:2608.06490v1 Announce Type: new Abstract: We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise
arXiv:2608.07457v1 Announce Type: new Abstract: What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new
Introducing Muse Glimmer Meta are back in the open weights game! Muse Glimmer is a brand new 30B model under a clean Apache 2.0 license (a step up from the janky Llama licenses of old). They claim to
arXiv:2608.06506v1 Announce Type: new Abstract: Language models are often evaluated as though capabilities demonstrated in English remain equally available when the same content is presented in other
arXiv:2608.07110v1 Announce Type: cross Abstract: Test-time training (TTT) views sequence modeling as an online learning problem in which fast weights are updated by an internal learning rule. Despite
arXiv:2608.06713v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) accelerate drug discovery, but standard pipelines assume query molecules already exist as graph entities, leaving unre
arXiv:2608.07040v1 Announce Type: new Abstract: Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations. While recent works ha
VLX-Seek-1.5-10B VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios. It targets practical setting
arXiv:2603.06054v2 Announce Type: replace-cross Abstract: The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their r
arXiv:2510.09717v3 Announce Type: replace-cross Abstract: Identifying training data of large-scale models is critical for copyright litigation, privacy auditing, and ensuring fair evaluation. However,
arXiv:2608.07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters,
arXiv:2608.06409v1 Announce Type: cross Abstract: Speech language models are increasingly evaluated on paralinguistic tasks by the accuracy of prompted answers, but answer accuracy combines failures a
arXiv:2608.06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., cl
arXiv:2608.07317v1 Announce Type: cross Abstract: The AI-Native Manifesto envisions large-scale agile software development in which humans increasingly govern intent, risk, and exceptions while agents
arXiv:2608.06704v1 Announce Type: new Abstract: Delegating a web task involves more than asking a question; it requires transferring a policy: what to verify, how to handle uncertainty, which preferen
arXiv:2608.07261v1 Announce Type: new Abstract: Large language models (LLMs) can solve complex multi-hop problems yet exhibit puzzling failures on simple two-hop queries: although a model may correctl
Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production environments. Quantization
The future of FDE work seems closely related with all work around evals/posttraining/RL envs. FDEs are effectively responsible for the following: 1. Define the business problem. 2. Codify the business
arXiv:2601.03895v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a popular algorithm for reinforcement learning with large language models (LLMs). How
arXiv:2608.05592v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation m
arXiv:2608.05375v1 Announce Type: new Abstract: Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but reliable deployment is often constrained by scarce,
Hey peeps. I know you're tired of low quants giving hard to believe numbers. I'm quite skeptical too and from what I tried I'm often left with the impression that the claims fall short. So this model
arXiv:2608.06108v1 Announce Type: new Abstract: Investment competence is inherently personalized: the same market evidence can justify different actions for investors with different goals, horizons, p
arXiv:2608.05806v1 Announce Type: cross Abstract: While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optima
arXiv:2608.05715v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as planners in robotic systems, where they translate natural-language commands into executable
arXiv:2608.06041v1 Announce Type: cross Abstract: Large language models (LLMs) have been shown to exhibit strong Python preferences when generating project-level code, but there is currently no system
arXiv:2601.21124v2 Announce Type: replace-cross Abstract: Current multimodal LLMs process audio as a mono stream, ignoring the rich spatial information essential for embodied AI. Existing spatial audi