Knowledge catalogue
arXiv:2609.12079v1 Announce Type: cross Abstract: Hierarchical correlations are a universal feature of any realistic model of data, and the question of how associative memory models may learn these co
Huh. This number is way off. You’re comparing one human brain to an entire data center capable of training new models. The actual answer is: IQ points per watt: Humans: 5 AI: 7 - 40 (!!) By my rough c
arXiv:2609.12712v1 Announce Type: new Abstract: Relational table learning has recently emerged as an important research direction for modeling multiple tables connected through primary key-foreign key
Introducing PC-ALM, a local-learning alternative to backpropagation. Our method trains 1000-layer neural nets using only local dynamics, and without backprop. Blog: https://pub.sakana.ai/pc-alm/ Stand
arXiv:2609.12127v1 Announce Type: new Abstract: Prompt-policy editing offers a practical way to improve agents that synthesize executable workflows without updating the underlying model. However, pers
arXiv:2609.12327v1 Announce Type: cross Abstract: Reservoir computing (RC) trains only a linear readout over a fixed recurrent layer, making it fast and data-efficient for online prediction. However,
arXiv:2510.15435v2 Announce Type: replace-cross Abstract: Bayesian optimisation (BO) enables sample-efficient global optimisation of expensive black-box functions but remains challenging in high dimen
arXiv:2609.12517v1 Announce Type: new Abstract: Long-Video Question Answering (LVQA) requires locating decisive evidence in hour-scale videos under a limited frame budget. Most training-free methods a
arXiv:2602.07181v4 Announce Type: replace Abstract: User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet reliably leveraging preference signals remains under
arXiv:2609.13040v1 Announce Type: new Abstract: We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable. Motiv
arXiv:2609.12123v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is an effective approach for adapting large pretrained models by learning low-rank weight updates. In practice, the LoRA rank
arXiv:2609.12317v1 Announce Type: new Abstract: A central question in LLM reasoning is whether reinforcement learning (RL) instills genuinely new capabilities or merely reshapes how existing knowledge
arXiv:2609.12531v1 Announce Type: new Abstract: In streaming tasks, recurrent models can carry latent computation across time, allowing each update to build on representations produced earlier. This r
arXiv:2603.07357v3 Announce Type: replace Abstract: Latent generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals a
arXiv:2601.04339v3 Announce Type: replace Abstract: Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T
arXiv:2609.10964v1 Announce Type: new Abstract: Agentic LLM workflows consist of sequences of model turns interleaved with tool interactions, so their end-to-end completion time depends not only on in
Interesting paper to improve recurrent reasoning. Looped models are great because you get more reasoning out of a model without adding parameters. So this work proposes a looped architecture with a ne
arXiv:2606.13720v2 Announce Type: replace Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recove
AuK-Flash: Fast 4-Step Speech Generation and Editing arXiv : https://arxiv.org/abs/2609.08936 Full Paper : https://arxiv.org/pdf/2609.08936 GitHub : https://github.com/Tencent-Hunyuan/AuK Project : ht
arXiv:2609.11282v1 Announce Type: new Abstract: Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know wheth
arXiv:2609.11231v1 Announce Type: cross Abstract: This paper presents SurgicalRoomAgent, a voice-interactive multi-agent system for smart operating rooms based on large language models (LLMs). The sys
arXiv:2609.11697v1 Announce Type: new Abstract: Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in general-purpose robotic manipulation, yet their gen
arXiv:2609.11126v1 Announce Type: new Abstract: Verification and validation (V&V) of classification models is crucial to enable a wide range of sensor processing applications. Currently, the V&V proce
arXiv:2609.11744v1 Announce Type: cross Abstract: Prefix caching can reduce the time to first token (TTFT) of long-context LLM requests by reusing previously computed key-value (KV) states, but for sh
arXiv:2609.10744v1 Announce Type: cross Abstract: Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank info
arXiv:2609.09475v1 Announce Type: cross Abstract: Existing physical-layer authentication (PLA) schemes for non-terrestrial networks (NTNs) often rely on single-anchor verification, lack joint authenti
arXiv:2404.13381v2 Announce Type: replace Abstract: The COVID19 pandemic had enormous economic and societal consequences. Contact tracing is an effective way to reduce infection rates by detecting pot
arXiv:2609.11331v1 Announce Type: new Abstract: Cyber-Physical Systems (CPS) are commonly represented through multiple interconnected models. During development, CPS consistency requires that shared m
arXiv:2609.11507v1 Announce Type: new Abstract: Multi-subject video generation faces two key challenges: uncontrollable fidelity strength and potential semantic drift. We address these by analyzing th
arXiv:2609.11656v1 Announce Type: new Abstract: The transition from file storage to database management systems transformed stored data into managed resources. AI now faces an analogous transition fro
arXiv:2609.11717v1 Announce Type: new Abstract: Unified models for object detection and trajectory forecasting aim to merge perception and prediction for autonomous driving, refining actor trajectorie
arXiv:2609.11561v1 Announce Type: new Abstract: Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inherently non-Markovian, requiring
arXiv:2609.11335v1 Announce Type: new Abstract: As large language models are increasingly deployed in sensitive domains, anonymizing input data to protect personally identifiable information has becom
I can't stand kv cache quantization. Even at q8_0, I can feel the difference. But realistically, when running Qwen3.8-27B-UD-Q4_K_XL on my 32 GB GPU, I only have room for ~170k tokens (with mtp and mm
arXiv:2609.09219v1 Announce Type: cross Abstract: AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Discovery Certification Protocol
arXiv:2607.18116v2 Announce Type: replace-cross Abstract: Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim. Howev
arXiv:2609.09348v1 Announce Type: cross Abstract: Managing resources across IoT, edge, and cloud layers calls for continuous, context-aware decisions under constraints that rarely stay fixed. Deep rei
arXiv:2601.19285v3 Announce Type: replace Abstract: Diffusion models achieve remarkable generation quality, yet face a fundamental challenge known as memorization, where generated samples can replicat
arXiv:2609.11414v1 Announce Type: new Abstract: Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing
arXiv:2609.11838v1 Announce Type: new Abstract: Cardiovascular screening models trained on national health surveys routinely report areas under the receiver operating characteristic curve (AUROC) near
arXiv:2609.10951v1 Announce Type: cross Abstract: AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verificati
arXiv:2609.11801v1 Announce Type: new Abstract: Humans and machines often solve harder problems by spending more time on computation. In deep learning, looped models implement this idea during inferen
arXiv:2001.03346v4 Announce Type: replace-cross Abstract: We propose a novel framework for learning time-varying graphs from spatiotemporal measurements. Given an appropriate prior on the temporal beh
arXiv:2609.10613v1 Announce Type: cross Abstract: In-context learning (ICL) jailbreaks reveal a critical vulnerability in multimodal large language models (MLLMs): harmful demonstrations in the prompt
arXiv:2609.09418v1 Announce Type: new Abstract: World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although
arXiv:2609.10187v1 Announce Type: new Abstract: In this work, we introduce language-aligned motion representations for domain-generalizable UPDRS-Gait severity estimation, aiming to learn semantically
arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame
arXiv:2609.08166v1 Announce Type: cross Abstract: The twenty-first century's transformative technology, artificial intelligence, is increasingly constrained by the twentieth century's transformative t
arXiv:2609.09884v1 Announce Type: new Abstract: Recent advances in Intrinsic Image Decomposition (IID) have increasingly relied on generative models. However, progress remains limited by three key cha
arXiv:2602.14488v3 Announce Type: replace-cross Abstract: IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive
arXiv:2609.07107v1 Announce Type: new Abstract: Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges for video understanding that conventional benchm
arXiv:2609.06853v1 Announce Type: cross Abstract: Shared key--value (KV) cache reuse improves large language model (LLM) serving, but it can also create a timing side channel that reveals whether a pr
Together AI announced the launch of “ThunderKittens” running on the NVIDIA Vera Rubin NVL72 platform, highlighting new performance gains and future directions. The announcement was shared via their Tw
Artificial intelligence-native cloud infrastructure giant CoreWeave Inc. says it’s going to help enterprise engineering teams to implement AI directly into their workflows through its new Physical AI
arXiv:2503.12497v2 Announce Type: replace-cross Abstract: Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. Timely prevent
Deepseek-V4.1-Flash is available now on Fireworks! It is a 552B Parameter MoE built for coding, cybersecurity, and agents. It is the ideal workhorse model that outperforms Opus 5 and GPT 5.6 Sol at 1/
Original Source from DeepSeek WeChat Official Account: https://mp.weixin.qq.com/s/qg0NU3NNUbp1co2PdkAPAg Today we're officially releasing the DeepSeek V4.1 Flash model. It is the smallest model in our
arXiv:2609.10308v1 Announce Type: new Abstract: Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability. In th
arXiv:2609.08186v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed t
arXiv:2609.05553v1 Announce Type: new Abstract: Agent memory allows LLM agents to use earlier interactions when answering new queries. Existing methods often compress interaction histories into summar