research

arXiv:2606.05610v1 Announce Type: new Abstract: The efficacy of continued pre-training for Large Language Models (LLMs) hinges upon hyperparameter configurations, such as learning rate and batch size.

arXiv:2606.05663v1 Announce Type: new Abstract: Conventional multirotors suffer from a rapid collapse of attainable wrench space (AWS) under abrupt total rotor failures, rendering full 6-DOF recovery

arXiv:2606.06033v1 Announce Type: new Abstract: Learning dexterous manipulation requires demonstrations that preserve fine hand-object interactions while remaining executable at deployment. Existing p

Really excited to be part of this journey and team 🚀 Ever since @SakanaAILabs inception, we have been discovering stepping stones for a fundamental 'AI² paradigm shift': Leveraging AI systems to impro

arXiv:2606.06428v1 Announce Type: new Abstract: Prior work has shown that large language models (LLMs) can translate unseen or low-resource languages by undergoing continued training or even by encodi

arXiv:2601.02880v2 Announce Type: replace-cross Abstract: Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no w

arXiv:2606.05858v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new avenues for generating training-free text embeddings. However, the causal attention in d

arXiv:2606.06443v1 Announce Type: new Abstract: Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it rema

arXiv:2606.06176v1 Announce Type: new Abstract: Underwater Image Enhancement (UIE) is essential for mitigating degradations caused by water medium. Although learning-based methods have advanced signif

arXiv:2606.06228v1 Announce Type: new Abstract: Training-free image editing has recently attracted increasing attention due to its ability to modify real images using powerful pre-trained diffusion an

arXiv:2606.06199v1 Announce Type: new Abstract: Standard segmentation metrics such as Dice and Hausdorff distance measure geometric overlap but say nothing about whether a segmented surface is suitabl

arXiv:2606.05912v1 Announce Type: new Abstract: Modeling dynamic facial expressions using 3D Gaussian representations remains challenging due to their unstructured nature. Conventional Gaussian avatar

arXiv:2503.22929v3 Announce Type: replace Abstract: Face anti-spoofing (FAS) techniques aim to enhance the security of facial identity authentication by distinguishing authentic live faces from decept

arXiv:2306.09712v2 Announce Type: replace-cross Abstract: In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline. Online methods explore

Some billionaires (or their foundations) do fund certain areas of basic research. Examples: Simons Foundation, Moore Foundation, Sloan Foundation, Keck Foundation, Schmidt Sciences, and several others

arXiv:2601.22580v2 Announce Type: replace Abstract: The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placeme

arXiv:2605.05367v2 Announce Type: replace Abstract: Existing 3D sign language avatar reconstruction methods are developed and evaluated exclusively on Western sign languages, and no 3D parametric anno

arXiv:2606.05328v1 Announce Type: cross Abstract: Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet

arXiv:2606.06188v1 Announce Type: new Abstract: Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reaso

arXiv:2606.05375v1 Announce Type: new Abstract: Optical coherence tomographic angiography (OCTA) is a powerful technique for imaging retinal microvasculature. However, acquiring reliable quantificatio

To be clear: there should not be a president of AI (let alone me 😅). Which is pretty much one point I make in the video. This reminder is about the content of the video, which is 3 years old, but ever

arXiv:2606.05846v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) has become a key technology for human--AI interaction. However, code-switching ASR (CS-ASR) remains particularly chal

arXiv:2602.03410v2 Announce Type: replace Abstract: Recent advances in large-scale diffusion models have intensified concerns about their potential misuse, particularly in generating realistic yet har

arXiv:2507.12336v2 Announce Type: replace Abstract: Most existing 3D keypoint estimation methods rely on manual annotations or calibrated multi-view images, both of which are expensive to collect. Thi

arXiv:2606.06444v1 Announce Type: cross Abstract: Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. Whi

arXiv:2603.14210v2 Announce Type: replace Abstract: We present Vavanagi, a community-run platform for Hula (Vula'a), an Austronesian language of Papua New Guinea with approximately 10,000 speakers. Va

arXiv:2606.06369v1 Announce Type: new Abstract: Learning-driven Scene Graph Generation (SGG) models excel on frequent relation types but degrade sharply under annotation sparsity, failing to capture r

arXiv:2606.05572v1 Announce Type: cross Abstract: We address the challenge of engineering distributed haptic displays capable of reproducing multiple localized, independently addressable vibrations --

We had to make some deep level changes to Hermes Update command this morning. It may require a number of you to run hermes update twice in a row (where you'll see an error the first time) Please run i

The Fast Fourier Transform (FFT) is a computationally efficient algorithm that converts time-domain signals into their frequency-domain representation, reducing computational complexity from O(n²) to

arXiv:2406.12620v3 Announce Type: replace Abstract: Do architectural and training differences influence the way models represent and process language? Traditional similarity metrics tell us whether tw

arXiv:2606.05533v1 Announce Type: cross Abstract: Existing robot planning systems rely on appearance-based reasoning, where visual observations are encoded into latent spaces organized around object a

arXiv:2606.05626v1 Announce Type: new Abstract: Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence f

arXiv:2606.06160v1 Announce Type: cross Abstract: RoPE-trained transformers distinguish absolute position in their attention patterns, even though RoPE encodes only relative offsets in the inner produ

arXiv:2606.06467v1 Announce Type: new Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate l

arXiv:2606.04836v1 Announce Type: new Abstract: Accurate Autism Spectrum Disorder (ASD) screening for school-age children is crucial to identify cases that may have been missed earlier and to enable t

arXiv:2606.04828v1 Announce Type: new Abstract: This paper presents a French corpus annotated for multiword expressions (MWEs) with adverbial function. This corpus is designed for investigation on inf

arXiv:2606.04946v1 Announce Type: cross Abstract: Consistency is an important property in dynamic submodular maximization and entails maintaining a near-optimal solution at all times, making only a sm

arXiv:2512.06553v2 Announce Type: replace-cross Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated b

arXiv:2606.04619v1 Announce Type: new Abstract: We propose MONIR, a Modalized-Output Normative Intermediate Representation for ASP-based compliance reasoning. Its core fragment has a staged operationa

arXiv:2606.04177v1 Announce Type: cross Abstract: Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert us

arXiv:2606.04877v1 Announce Type: cross Abstract: Proof assistants based on expressive logics suffer limited automation for proof search, raising the cost of formal verification based on proof assista

arXiv:2606.04189v1 Announce Type: new Abstract: Aspect-Based Sentiment Analysis (ABSA) requires high-quality datasets to train reliable models. However, existing annotation tools treat output as flat

arXiv:2604.08438v2 Announce Type: replace Abstract: The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standi

arXiv:2006.04013v6 Announce Type: cross Abstract: Artificial Intelligence (AI) has been adopted in a wide range of domains. This shows the imperative need to develop means to endow common people with

arXiv:2606.04980v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expe