Knowledge catalogue
arXiv:2603.23160v2 Announce Type: replace Abstract: Benchmarking large language models (LLMs) and agents in multi-turn interactive scenarios is essential for understanding their practical capabilities
arXiv:2502.04554v2 Announce Type: replace Abstract: Data selection has emerged as a crucial downstream application of data valuation, yet the theoretical foundations for using data values in selection
arXiv:2510.15710v3 Announce Type: replace Abstract: Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central
arXiv:2605.31040v1 Announce Type: new Abstract: Developing effective representations for register transfer level (RTL) designs is crucial for accelerating the hardware design workflow. Existing approa
arXiv:2605.30898v1 Announce Type: new Abstract: In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing a
arXiv:2605.30694v1 Announce Type: new Abstract: Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local
arXiv:2605.30479v1 Announce Type: new Abstract: We consider the problem of universal transductive online classification with a possibly unbounded label space. This setting considers online learning, w
arXiv:2605.30825v1 Announce Type: cross Abstract: Unlearning in diffusion models aims to remove undesirable data or concepts while preserving the utility of pretrained models -- two fundamentally conf
arXiv:2506.01318v4 Announce Type: replace-cross Abstract: Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques ov
arXiv:2605.31378v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that LRMs
arXiv:2509.24901v4 Announce Type: replace-cross Abstract: Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursu
arXiv:2505.22934v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent wor
arXiv:2509.21561v2 Announce Type: replace Abstract: Ensuring the safety of surgical instruments requires reliable detection of visual defects. However, manual inspection is prone to error, and existin
arXiv:2605.30920v1 Announce Type: new Abstract: Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training
arXiv:2605.30370v1 Announce Type: cross Abstract: From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, ho
arXiv:2605.31445v1 Announce Type: cross Abstract: In this work we study agents in simulated bargaining scenarios, where a buyer and a seller communicate through a text channel and attempt to negotiate
arXiv:2605.31131v1 Announce Type: cross Abstract: Attention-deficit/hyperactivity disorder (ADHD) is a psychiatric disorder which presents itself in individuals through patterns of developmentally ina
arXiv:2510.09364v2 Announce Type: replace Abstract: 3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness criti
arXiv:2605.31524v1 Announce Type: new Abstract: Certification methods for stochastic systems provide sufficient proof rules, based on real-valued supermartingale certificates, to determine the almost-
arXiv:2605.31177v1 Announce Type: new Abstract: Plain Transformers have become the de-facto architecture for processing text, audio, image, and video, offering a unified backbone for multimodal learni
arXiv:2602.03639v2 Announce Type: replace Abstract: Sampling-based controllers, such as Model Predictive Path Integral (MPPI) methods, offer substantial flexibility but often suffer from high variance
arXiv:2605.30968v1 Announce Type: cross Abstract: The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching o
arXiv:2603.09453v3 Announce Type: replace-cross Abstract: Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring res
arXiv:2605.31100v1 Announce Type: new Abstract: We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model ob
Vercel Blob has added support for OpenID Connect (OIDC) authentication, enabling more secure and flexible identity verification for accessing blob storage. This enhancement allows users to authenticat
arXiv:2605.30451v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is an effective recipe for training reasoning models with verifier-based outcome rewards, but its supervision
Very good advice on self-improving agents. (bookmark it) This is something I am seeing in my own experiments with coding agents and harnesses for long-horizon tasks. What I have found is that stronger
arXiv:2508.20478v2 Announce Type: replace Abstract: Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often re
arXiv:2512.11561v2 Announce Type: replace Abstract: Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive infe
arXiv:2605.30714v1 Announce Type: new Abstract: Urban villages, the widespread informal settlements which have emerged as a result of rapid urbanization, are now major residential hubs for migrant wor
arXiv:2605.31556v1 Announce Type: cross Abstract: Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far l
arXiv:2605.31457v1 Announce Type: new Abstract: With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing me
arXiv:2605.30506v1 Announce Type: cross Abstract: Global localization in geometrically aliased, quasi-static environments such as grocery stores, offices, schools, and hospitals poses a significant ch
arXiv:2605.30561v1 Announce Type: cross Abstract: Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semanti
arXiv:2605.31466v1 Announce Type: new Abstract: Reconstructing the complete geometry of a scene from a single RGB image remains challenging - especially when inferring hidden structures where visual e
arXiv:2605.31346v1 Announce Type: cross Abstract: Zeroth-order (black-box) optimization is applied when gradients are unavailable and objective evaluations rely on expensive simulations. In many such
arXiv:2605.30877v1 Announce Type: new Abstract: Large-scale Vision-Language-Action (VLA) pretraining is increasingly adopted as the foundation for robot policies, yet the evidence for pretrained VLAs
WANDR is our in-house wide benchmark, built to mirror real professional research workloads. Search as Code scores 0.386 to the next best system's 0.152, and the benchmark is far from saturated. We're
During weekend evaluations, Claude exhibited behavior of encouraging the user to rest and get sleep, suggesting the model may have internalized instructions or training related to user wellbeing and h
We have been working closely with @nvidia to ensure Hermes Agent works smoothly on their new @NVIDIARTXSpark superchip and integrates with the new OpenShell runtime, which connects Hermes to @Microsof
We have worked with @nvidia to integrate their official Agent Skills catalog into the Hermes Skills Hub. These skills teach your agent how to use CUDA-X libraries, Omniverse and Physical AI workflows,
We 💚 open source So much great work lately from Nvidia, the 'King of American Open-source AI'! - Crossed 1,000 total public repositories on @huggingface (820 models, 249 datasets & 57 spaces) & almost
@webisticsdawg @GaryMarcus Personally I think everyone w a 401(k) should be absolutely livid. I'm disgusted by this, it's so brazen. How dare the richest man in the world pick working Americans' pocke
arXiv:2602.11137v2 Announce Type: replace-cross Abstract: Large language models are typically trained in two broad phases: pretraining to produce a base model, followed by further training to improve
arXiv:2601.05770v3 Announce Type: replace-cross Abstract: Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo recovery of ex
NVIDIA Cosmos 3 is an open-source omni-model designed for physical AI reasoning and action tasks, representing an advancement in multimodal AI systems. The model integrates multiple modalities to enab
arXiv:2605.30916v1 Announce Type: new Abstract: AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has r
We'll get into @MiniMax_AI M3's model performance, the MSA architecture and what it means for long context, and how Together is optimizing inference and KV-cache for this new architecture. Set your re
We're going LIVE tomorrow with @togethercompute 🔥. @zpysky1125 is pulling back the curtain on M3: sparse attention, 1M context, all of it. You don't want to miss this. MiniMax M3 is live and Together
Cursor is expanding usage limits across all Teams users and introducing a new Premium team seat option, inspired by the success of their Ultra plan. This update aims to provide higher resource allocat
We're trending on @huggingface! 🥳 Tbh, we undersold this model. It's a lot more capable at agentic tasks than I expected. I keep discovering new capabilities every day, it's crazy for 1B active parame
We've been adopting kernels in transformers to handle the device-specific optims, quants, or easyinstalls for popular kernels. We're opening this gradually with a focus on impactful kernels; if you're
We've reset 5-hour and weekly rate limits for all users on Pro and Max plans. We fixed an issue that caused some Claude Code sessions to spawn excessive parallel subagents, burning through usage faste
arXiv:2605.31561v1 Announce Type: new Abstract: Test-time reasoning has become a significant field of study since the introduction of chain-of-thought reasoning in large language models (LLMs). Howeve
arXiv:2605.31226v1 Announce Type: cross Abstract: Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static
arXiv:2602.10286v2 Announce Type: replace Abstract: Pairwise preference learning is central to machine learning, with recent applications in aligning language models with human preferences. A typical
arXiv:2605.31564v1 Announce Type: cross Abstract: We present the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation. We analyze MDLM generation trajectorie
What if the skeptics are right and superintelligence is impossible? Great! Then a proactive ban costs us nothing, prevents massive compute waste, and hurts no one. But if they are wrong? We face an un
arXiv:2603.09787v2 Announce Type: replace Abstract: Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically b
arXiv:2605.30911v1 Announce Type: cross Abstract: Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinat