CE^4L: Continual Ego, Exo, and Ego-Exo Learning
arXiv:2609.23492v1 Announce Type: new Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shif
Knowledge catalogue
arXiv:2609.23492v1 Announce Type: new Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shif
arXiv:2609.22684v1 Announce Type: cross Abstract: Memory-dependent robotic manipulation often requires later actions to use information from earlier interactions. Existing vision-language-action (VLA)
arXiv:2609.21651v1 Announce Type: cross Abstract: Farmer.Chat is Digital Green's farm advisory service for smallholder farmers. When something looks wrong with a crop, the farmer takes a photograph an
Hi all! After all the jev hype I wanted to try by myself and got qwen3.8 27b to mix-and-match open implementations on top of ninfer, and to be honest I'm quite impressed with the results, latency is n
arXiv:2609.21346v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) scales capacity, but existing designs cannot set three quantities independently. For a single token, participation is how many
What I like about Jev: for years, large generalist models sucked almost all the oxygen out of AI. But there are huge opportunities in much more specialized and customized models, built for specific ta
Live now: our Inference Engineering Track from AI Engineer World's Fair 2026. A benchmark tool told to run 200 queries a second that ran 38 and reported 200. A model that answered one prompt in a thou
Welcome to http://trumanworld.live An infinite live stream running inside a persistent AI world engine, powered by GPT-6 Astra and #MiniMax H3 Max Director by @fal Truman World is an AI-generated simu
Amazon SageMaker AI shipped 13 inference launches in the first half of 2026 across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. This post reviews each launch,
arXiv:2603.21925v2 Announce Type: replace Abstract: In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat e
arXiv:2609.19721v1 Announce Type: new Abstract: Clinical coding agents repeatedly encounter the same failure modes, including unsupported codes, missed documented conditions, specificity errors, and p
arXiv:2609.20177v1 Announce Type: new Abstract: Forecasting corporate tax avoidance proxies from firm--year panel data is challenging because predictive signals are distributed across short firm histo
arXiv:2609.20455v1 Announce Type: new Abstract: External skills provide domain procedures without parameter updates, but existing methods often edit skills directly from failed rollouts without struct
arXiv:2609.19671v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and un
arXiv:2609.19393v1 Announce Type: new Abstract: Work zones alter lane geometry through temporary traffic controls and closures that may be absent from on-board maps, challenging autonomous vehicle (AV
arXiv:2609.18219v1 Announce Type: cross Abstract: Quantum Reinforcement Learning (QRL) represents policies as variational quantum circuits (VQCs), making it attractive for combinatorial optimization s
arXiv:2609.18909v1 Announce Type: cross Abstract: Agent benchmarks are substantially more costly to evaluate than conventional LLM benchmarks. Benchmark compression is therefore a natural solution, ye
arXiv:2602.03994v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains unde
arXiv:2609.17921v1 Announce Type: new Abstract: Vision-language model (VLM) agents combine specialized perception, tools, and reasoning to address complex visual tasks. In multi-agent settings, differ
arXiv:2609.18460v1 Announce Type: new Abstract: How does a multi-agent system evolve from a local deviation into collective loss of control? We propose an epidemic explanation organized around acciden
arXiv:2609.18852v1 Announce Type: new Abstract: Longitudinal electronic health records (EHRs) capture years of patient history across notes, codes, labs, and procedures, and contain evidence needed to
arXiv:2609.18069v1 Announce Type: new Abstract: Underwater semantic segmentation is essential for marine ecosystem monitoring, yet remains challenging due to severe visual degradation. Light absorptio
arXiv:2609.17547v1 Announce Type: new Abstract: AI assistants are expected to remain useful during difficult interactions, but little is known about how repeated verbal abuse changes their engagement
arXiv:2609.17777v1 Announce Type: cross Abstract: AI and large language models can recover clinically meaningful features from electronic health records (EHRs), but predictive usefulness does not esta
arXiv:2609.18176v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly w
arXiv:2609.17709v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems typically employ fixed retriever and generator configurations across queries, despite substantial differe
arXiv:2609.18134v1 Announce Type: cross Abstract: Methodological progress in artificial intelligence (AI) for electronic health records (EHRs) depends on our ability to determine which algorithms work
arXiv:2609.18949v1 Announce Type: cross Abstract: We introduce StableEval Arena, a cost-aware benchmark framework for evaluating agentic AI systems on stablecoin peg-risk prediction. StableEval Arena
Hi Ollama Team, I’m writing regarding the announced retirement of GLM-5.1 from Ollama Cloud on 25 September 2026. I wanted to provide some fairly detailed technical feedback because GLM-5.1 is not sim
arXiv:2609.18453v1 Announce Type: new Abstract: A calibrated Vision-Language Model (VLM) can repeatedly self-correct, say 'Wait, I should recheck,' arrive at the wrong answer, and still report high co
arXiv:2602.00408v3 Announce Type: replace-cross Abstract: This paper proposes a novel Variational Graph-to-Scheduler (VG2S) framework for solving the Job Shop Scheduling Problem (JSSP), a critical tas
arXiv:2609.17857v1 Announce Type: cross Abstract: Who the judge is can affect an LLM-as-judge result, but measuring that effect without confusing it with candidate quality is difficult. We study four
arXiv:2609.16890v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods of
arXiv:2609.16755v1 Announce Type: new Abstract: Brain tumor segmentation remains difficult because enhancing tumor (ET) has low contrast and overlaps surrounding tissue, while scanner and site variati
arXiv:2609.17193v1 Announce Type: new Abstract: Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference, motivating the deployment of LLMs across distributed e
arXiv:2609.16454v1 Announce Type: new Abstract: Recent work by Doshi and Hauser (2024), Bisbee et al. (2024), and Xie et al. (2026) raises concerns that outputs from large language models (LLMs) tend
GitHub: https://github.com/pfekin/LARA I've been working on LARA (Lightweight Additive Residual Adaptation), a research project on making post-training modular for frozen language models. I've also de
arXiv:2609.16599v1 Announce Type: cross Abstract: Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large lang
arXiv:2609.16459v1 Announce Type: cross Abstract: Privileged on-policy distillation improves multimodal reasoning by allowing a teacher to evaluate student trajectories using rich, training-only visua
arXiv:2609.17130v1 Announce Type: new Abstract: Dynamic facial expression recognition (DFER) benchmarks such as DFEW provide multiple annotator votes per clip, yet most models collapse them to a major
arXiv:2609.16427v1 Announce Type: new Abstract: This paper presents a Belarusian-specific data-cleaning pipeline and fine-tuning for English-Belarusian machine translation. Our cleaning pipeline disti
arXiv:2609.16936v1 Announce Type: cross Abstract: Large language model (LLM)-powered coding agents have made rapid progress in automating software engineering tasks, yet repository-level issue resolut
arXiv:2609.13481v1 Announce Type: new Abstract: Large language models have made abstractive summarization remarkably fluent, but generated summaries can hallucinate facts, posing serious risks in biom
arXiv:2609.14741v1 Announce Type: cross Abstract: Early thermal-mechanical lattice requirements are knowledge-intensive and often jointly unsatisfiable: an engineer asks for a cell that is light, stif
arXiv:2607.19223v2 Announce Type: replace-cross Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified by the target model, has becom
arXiv:2609.13149v1 Announce Type: cross Abstract: For local large language model agents, active context is a scarce resource: memory capacity, prefill latency, cache growth, and service objectives all
arXiv:2609.15009v1 Announce Type: new Abstract: Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better ov
arXiv:2609.13651v1 Announce Type: cross Abstract: Robot deployments rarely change one mechanism at a time: cameras, action interfaces, and physical dynamics often shift together. Prior adaptation reci
arXiv:2606.22906v2 Announce Type: replace-cross Abstract: Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remain
arXiv:2609.14715v1 Announce Type: new Abstract: We scale our conventional sub-150M pretraining recipe from 53.5M to 109.7M parameters, holding the method fixed (Qwen3-style decoder with grouped-query
arXiv:2609.13737v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed, the generation of harmful content has become a critical safety concern. Existing safeguards o
arXiv:2609.13282v1 Announce Type: new Abstract: Industrial anomaly localization has advanced rapidly with feature-based, reconstruction-based, and distillation-based methods. Most of these methods sco
arXiv:2603.09232v2 Announce Type: replace-cross Abstract: While Contrastive Decoding (CD) has been proposed to enhance Large Audio Language Models (LALMs), it has not been evaluated at scale, and the
arXiv:2609.15794v1 Announce Type: new Abstract: Clinical AI systems are evaluated with instruments built for research settings (reference-based similarity metrics and expert rubric panels) that measur
arXiv:2609.13182v1 Announce Type: cross Abstract: Robert Smithson's 1970 land artwork Spiral Jetty, located in the north arm of Utah's Great Salt Lake, has alternated between submergence and exposure
arXiv:2609.15224v1 Announce Type: new Abstract: We present LOVER, a nderline{L}ong to shnderline{O}rt nderline{V}ideo nderline{E}vidence nderline{R}einforced model for grounded question answering (GQA
arXiv:2609.13692v1 Announce Type: cross Abstract: LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces -- retrieved passages, tool definitions
arXiv:2609.14773v1 Announce Type: new Abstract: As LLM conversations grow to hundreds of turns, full-context injection incurs O(N^2) cumulative token costs, while lossy summarization or hard truncatio
arXiv:2609.13224v1 Announce Type: new Abstract: Autonomous vehicles are expected to improve road safety and efficiency, but passengers often remain uncertain about what the vehicle perceives and why i
arXiv:2609.13231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existing fine-tuning methods provide