Knowledge catalogue
arXiv:2605.16767v1 Announce Type: new Abstract: Multi-label legal annotation requires assigning multiple labels from large, evolving taxonomies to long, fact-intensive documents, often under limited s
arXiv:2602.10134v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive informatio
arXiv:2605.17787v1 Announce Type: new Abstract: It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptive optimizers such as Adam in pre-training Large La
arXiv:2603.11276v2 Announce Type: replace-cross Abstract: Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. Ho
arXiv:2605.18174v1 Announce Type: new Abstract: Muon has recently emerged as a strong alternative to AdamW for training neural networks, with encouraging large-scale pretraining results and growing ev
arXiv:2509.21319v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in
arXiv:2603.04639v2 Announce Type: replace-cross Abstract: Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipula
arXiv:2508.13977v3 Announce Type: replace Abstract: Depth estimation is a fundamental component of spatial perception for autonomous driving and other unmanned systems operating in open urban environm
rsi is here. jesus https://x.com/nickevanjoseph/status/2056760504949842219?s=46 Excited to welcome Andrej to the Pretraining team! He'll be building a team focused on using Claude to accelerate pretra
arXiv:2605.16843v1 Announce Type: new Abstract: India's Right to Information Act, 2005 gives every citizen the right to demand information from public authorities, yet in practice most people cannot m
arXiv:2605.17526v1 Announce Type: cross Abstract: As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end
arXiv:2605.17610v1 Announce Type: cross Abstract: The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deplo
arXiv:2510.18822v4 Announce Type: replace Abstract: Due to the varying granularity of target states across different tasks, most existing trackers are tailored to a single task, which specificity limi
arXiv:2605.18613v1 Announce Type: cross Abstract: Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio
arXiv:2605.16686v1 Announce Type: new Abstract: Knowledge editing (KE) provides a lightweight alternative to repeated fine-tuning of LLMs. However, most existing KE methods target dense feed-forward l
arXiv:2605.17582v1 Announce Type: new Abstract: Many natural and engineered time series -- equity returns, climate anomalies, turbulent velocities, neural recordings, packet-level network traffic -- a
arXiv:2510.26384v2 Announce Type: replace Abstract: The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative da
arXiv:2510.08702v2 Announce Type: replace Abstract: Code Large Language Models (LLMs) are revolutionizing software engineering. However, scaling laws that guide the efficient training are predominantl
arXiv:2605.16628v1 Announce Type: new Abstract: The SCARED dataset is a widely used benchmark for endoscopic depth estimation, offering ground-truth 3D reconstructions captured with a structured light
arXiv:2605.18454v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) has recently emerged as a promising approach to solve combinatorial optimization problems such as job shop schedulin
arXiv:2605.18630v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities acro
arXiv:2605.16883v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail t
arXiv:2501.01046v4 Announce Type: replace Abstract: Dataset deduplication is widely recognized as a crucial preprocessing step that enhances data quality and improves the performance of large language
arXiv:2605.18431v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively fro
arXiv:2605.17448v1 Announce Type: cross Abstract: Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: th
arXiv:2603.02218v2 Announce Type: replace-cross Abstract: Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are bett
arXiv:2605.17537v1 Announce Type: new Abstract: 3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reaso
arXiv:2605.17497v1 Announce Type: new Abstract: GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We
arXiv:2512.12598v3 Announce Type: replace Abstract: We focus on the foundational task of Scene Staging: given a reference scene image and a text condition specifying an actor category to be generated
arXiv:2605.18468v1 Announce Type: cross Abstract: We study approximation by shallow ReLU^s networks, sigma_s(t)=max{0,t}^s, and the generalization behavior of such networks under ell_1 path-norm contr
arXiv:2512.17843v4 Announce Type: replace-cross Abstract: By evaluating Large Language Models (LLMs) through uniform, text-only interfaces, current academic benchmarks obscure how the unique designs a
arXiv:2505.21893v3 Announce Type: replace-cross Abstract: Preference learning has garnered extensive attention as an effective technique for aligning diffusion models with human preferences in visual
arXiv:2605.18221v1 Announce Type: cross Abstract: Real-time magnetic resonance imaging (rtMRI) of speech production enables non-invasive visualization of dynamic vocal-tract motion and is valuable for
arXiv:2605.18693v1 Announce Type: new Abstract: As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether t
arXiv:2605.16986v1 Announce Type: cross Abstract: LLM agents benefit from reusable skills, yet test-time tasks often require guidance more specific than a static skill library can provide. We propose
arXiv:2605.18401v1 Announce Type: cross Abstract: Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills a
arXiv:2605.17949v1 Announce Type: new Abstract: Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoni
arXiv:2605.16626v1 Announce Type: cross Abstract: Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dan
arXiv:2604.08432v2 Announce Type: replace-cross Abstract: Photonic neural networks promise ultrafast inference, yet most architectures rely on linear optical meshes with electronic nonlinearities, rei
Google is transitioning from the Gemini CLI tool to a new CLI called AGY (Antigravity CLI), but this change has drawbacks: AGY is not open source and no longer supports ACP functionality, representing
arXiv:2605.17789v1 Announce Type: cross Abstract: Memory systems for AI assistants were built for single-user dialogue and fail characteristically when applied to multi-party social group settings. Th
Cybersecurity startup Sola Security Ltd. today announced the launch of Lumina, an autonomous risk intelligence platform that applies contextual artificial intelligence across cloud, identity, software
arXiv:2605.18232v1 Announce Type: cross Abstract: Somali is a Cushitic language of the Horn of Africa with ~25 million speakers, yet no documented dedicated Somali pretraining corpus with a companion
This X thread from Google AI showcases practical and creative applications of Gemini Omni, Google's multimodal AI model, as demonstrated and shared by the user community. The thread appears to be a cu
arXiv:2605.17710v1 Announce Type: new Abstract: Although modern multilingual Automatic Speech Recognition (ASR) systems support several Nigerian languages, their performance consistently lags behind h
arXiv:2602.03535v2 Announce Type: replace Abstract: We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsi
arXiv:2605.18209v1 Announce Type: cross Abstract: Spatial question answering over egocentric video is a challenging task that requires Vision-Language Models (VLMs) to reason about 3D object positions
arXiv:2605.17311v1 Announce Type: new Abstract: The remarkable visual fidelity of recent commercial video generative models, such as Sora and Veo, renders robust AI-generated video detection increasin
arXiv:2603.10935v4 Announce Type: replace-cross Abstract: Variational autoencoders (VAEs) frequently suffer from posterior collapse, where the latent variables become uninformative as the approximate
Spotify's Chief Architect just showed how they ship 4,5K deployments /day with Claude at Anthropic stage 27-minutes. free. By #1 music app dev 'More than 99% of our engineers use AI coding tools. Adop
arXiv:2605.17834v1 Announce Type: new Abstract: Diffusion models exhibit remarkable generative capability, but their high latency limits practical deployment. Many studies have attempted to reduce sam
arXiv:2605.18287v1 Announce Type: new Abstract: It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-
arXiv:2605.17273v1 Announce Type: cross Abstract: State-of-the-Art (SOTA) claims pervade Artificial Intelligence (AI) and Machine Learning (ML) research. These claims rest on benchmark evaluations, wh
arXiv:2605.18656v1 Announce Type: cross Abstract: Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-
arXiv:2511.19320v2 Announce Type: replace Abstract: Preserving first-frame identity while ensuring precise motion control is a fundamental challenge in human image animation. The Image-to-Motion Bindi
arXiv:2605.16470v1 Announce Type: cross Abstract: Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impractical due to its computational and memory demands
arXiv:2605.16381v1 Announce Type: cross Abstract: Proactive streaming video understanding requires models to continuously process video streams and decide when to respond, rather than merely what to r
arXiv:2605.16353v1 Announce Type: cross Abstract: Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT met
arXiv:2506.05442v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. Howe
arXiv:2605.17568v1 Announce Type: new Abstract: Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with