Knowledge catalogue
arXiv:2610.18724v1 Announce Type: new Abstract: The rapid advancement of image-to-text extraction systems and large language models (LLMs) poses new challenges for educational assessment by making ass
arXiv:2610.15159v1 Announce Type: new Abstract: Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly as
arXiv:2610.17824v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a principal recipe for improving the reasoning of large language models (LLMs). It rest
arXiv:2610.17183v1 Announce Type: cross Abstract: Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an
arXiv:2610.14025v1 Announce Type: new Abstract: Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that
arXiv:2610.17114v1 Announce Type: new Abstract: Frontier large language models (LLMs) now reason about space well enough to program robots, yet the world models behind robot policies are implicit, hel
arXiv:2610.16812v1 Announce Type: new Abstract: Symbolic regression (SR) aims to discover interpretable mathematical expressions from data and plays a key role in scientific discovery. However, existi
arXiv:2610.17214v1 Announce Type: new Abstract: What information does a reinforcement learning policy omit? At each state, a standard policy stores one probability per action. It has no place to recor
arXiv:2610.17853v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong performance on diverse vision-language tasks, but their computational demands limit deploy
arXiv:2610.15207v1 Announce Type: new Abstract: Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass sa
arXiv:2610.18451v1 Announce Type: cross Abstract: Large-scale expert parallelism (EP) has become the standard deployment configuration for Mixture-of-Experts (MoE) models in production. Meanwhile, the
arXiv:2601.22318v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models lo
arXiv:2610.16744v1 Announce Type: new Abstract: Video large language models (Video LLMs) encode each frame into hundreds of visual tokens, making video inference expensive. Existing methods reduce thi
arXiv:2610.15707v1 Announce Type: new Abstract: A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating
arXiv:2610.17794v1 Announce Type: new Abstract: Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external condition
arXiv:2610.17062v1 Announce Type: new Abstract: We propose a mitigation to reward hacking in reinforcement learning. Our setup involves a misspecified reward function that gives rise to unintended beh
arXiv:2610.16817v1 Announce Type: new Abstract: Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large language m
arXiv:2506.10946v3 Announce Type: replace Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing
arXiv:2610.17694v1 Announce Type: new Abstract: We introduce HelpMeOut, an embodied AI benchmark for error-aware monitoring of household task execution. Existing embodied household benchmarks typicall
arXiv:2603.29602v2 Announce Type: replace-cross Abstract: Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and close
arXiv:2610.16299v1 Announce Type: new Abstract: Video anomaly understanding (VAU) aims to generate language-level interpretations of anomalous events in long videos, requiring visual evidence that sup
arXiv:2610.14883v1 Announce Type: cross Abstract: We present MARL-BattleGrounds (MARL-BGs), an easy-to-use JAX-native benchmark for heterogeneous and competitive multi-agent reinforcement learning (MA
arXiv:2511.05319v3 Announce Type: replace Abstract: Despite remarkable progress in steganography, embedding sentence-level information into cover media remains challenging. In this work, we present th
https://preview.redd.it/gwb4of5vmivh1.png?width=2400&format=png&auto=webp&s=853f4cf25b4140ccf8b151b4124547788a544b33 UserRepGen-4B is a fine-tuned Qwen3.5-4B language model that generates a structured
arXiv:2610.17856v1 Announce Type: new Abstract: Time-series analysis is increasingly studied in multimodal settings, yet most benchmarks pair temporal signals with text or with visualizations derived
arXiv:2610.16212v1 Announce Type: new Abstract: Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared
arXiv:2610.16226v1 Announce Type: cross Abstract: Network decision-making tasks, including adaptive bitrate streaming, load balancing, and congestion control, require policies to process heterogeneous
arXiv:2610.16815v1 Announce Type: cross Abstract: Calibration has been extensively studied for classifiers, but remains largely unexplored for crowdsourcing aggregation methods, which are increasingly
arXiv:2508.06163v2 Announce Type: replace-cross Abstract: Merging multiple task-specific fine-tuned checkpoints into a single multi-task model provides an attractive alternative to joint multi-task tr
arXiv:2502.04356v2 Announce Type: replace-cross Abstract: In response to the success of proprietary Large Language Models (LLMs), there is a growing interest in developing open, non-proprietary LLMs a
arXiv:2610.14022v1 Announce Type: new Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confi
arXiv:2610.16592v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) is commonly used to enhance the capabilities of large language models (LLMs) in solving complex multi-turn tasks.
arXiv:2610.14474v1 Announce Type: new Abstract: Medication recommendations seek to deliver personalized drug combinations based on patients' clinical information, where ensuring transparent decision-m
arXiv:2610.15742v1 Announce Type: new Abstract: Scene classification of remote sensing imagery with multimodal large language models (MLLMs) is formulated as a single-forward-pass decision problem: ca
arXiv:2610.13999v1 Announce Type: new Abstract: Rule decisions such as content moderation, advertising compliance, and eligibility checks combine several conditions, exemptions, and missing-informatio
arXiv:2610.15204v1 Announce Type: cross Abstract: Large language models are increasingly used in computer science education. However, the teaching abilities of even the most powerful LLMs are limited:
arXiv:2610.16533v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is reshaping how large language models (LLMs) acquire reasoning capabilities, yet the optimizers
arXiv:2508.04451v2 Announce Type: replace Abstract: Red teaming is essential for securing Large Language Models, yet current automated methods remain limited by templates and single-turn attacks. To s
arXiv:2610.15098v1 Announce Type: new Abstract: Text-to-video (T2V) models are highly sensitive to prompt specificity, while iterative prompt optimization typically improves generation quality only th
arXiv:2610.15365v1 Announce Type: cross Abstract: Large language models (LLMs) can produce harmful content while generating a response. A useful safeguard should not only detect this risk during gener
arXiv:2610.14184v1 Announce Type: new Abstract: Studying model training requires checkpoint trajectories, whose storage cost limits temporal resolution. Although adjacent checkpoints are numerically c
We just shipped web search in Private Mind, our open source app for running LLMs locally on iOS and Android. The video is the whole pitch: Qwen 3 1.7B with web off makes up Apple's September event, wi
arXiv:2610.14958v1 Announce Type: cross Abstract: Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later. Fa
arXiv:2610.16020v1 Announce Type: new Abstract: Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers. We ask under what assu
I'm a first year ML PhD at a T5 ML program in the US. I managed to get a first author paper accepted to NeurIPS Main Track last month and thought I'd start applying for PhD research internships since
David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a
Every few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: shou
A coding agent finishes a change and wants to open a GitHub issue with a link to its results. The agent can describe the issue, but creating it belongs to a different system. It needs a tool that can
When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside
Hi, I see that vllm released d3 (a family of decision models) and llama.cpp already has support for them. I want to try them out. Are decision models sensitive to quantization? I know that for autocom
I’ve wanted this for a long time: a Krea-2 model that gives you a magazine page in one shot. Flash-lit gravure sets, film grain, multi-photo layouts on white paper, big headlines, covers and back cove
arXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re
arXiv:2610.13708v1 Announce Type: new Abstract: Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only th
arXiv:2610.13455v1 Announce Type: new Abstract: Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has
arXiv:2610.12494v1 Announce Type: new Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key pr
arXiv:2610.12545v1 Announce Type: cross Abstract: Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revi
arXiv:2610.13862v1 Announce Type: new Abstract: Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-
arXiv:2610.12830v1 Announce Type: new Abstract: Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinfor
arXiv:2610.12815v1 Announce Type: new Abstract: RDMA can reduce communication overhead in distributed machine learning systems, but realizing these benefits in production requires more than replacing
arXiv:2610.12758v1 Announce Type: new Abstract: Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than