EGS
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Accelerating Min-Max Optimization via Power-Law Stepsizes
Announce Type: cross Abstract: We revisit the convergence guarantees of the Extragradient (EG) method for unconstrained biaffine min-max optimization. It is known that EG with a fixed stepsize achieves a $\Theta(T^{-1/2})$ last-iterate convergence rate, which is slower than the optimal $\mathcal{O}(T^{-1})$ rate attainable by incorporating additional mechanisms such as anchoring. Motivated by recent advances showing that dynamic stepsizes alone can significantly accelerate gradient descent,...
Recent Advances and Trends in Learning-based 3D Representations
arXiv:2606.04871v1 Announce Type: new Abstract: The selection of an appropriate 3D representation is a fundamental design decision that dictates the efficiency, quality, and capabilities of modern computer vision and graphics pipelines for tasks such as 3D reconstruction, novel-view synthesis and rendering, shape and motion analysis, recognition, and generation. While traditional representations (\eg meshes, point clouds, and volumetric grids) remain standard outputs of 3D sensors (\eg LiDAR...
HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping
Announce Type: replace Abstract: Visual loco-manipulation of arbitrary in-the-wild objects requires accurate end-effector (EE) control and a generalizable understanding of the scene from visual inputs (eg, RGB-D images). Existing imitation and sim2real methods jointly learn both these aspects via monolithic end-to-end learning and are thus hard to scale. In this work, we bring to bear the best tools for each of these problems -- large vision models for generalizable scene understanding and...
Integrated valorisation of PET and xylose using the oleaginous microorganisms Yarrowia lipolytica and Rhodococcus jostii
The increasing accumulation of polyethylene terephthalate (PET) waste has prompted the development of sustainable biotechnological strategies for its degradation and valorisation. This study presents an integrated approach combining enzymatic PET depolymerization by Yarrowia lipolytica, engineered to express and secrete the cutinase HiC and the lipase CalB, with the microbial valorization of PET-derived monomers, terephthalic acid (TPA) and ethylene glycol (EG), by Rhodococcus jostii RHA1....
From Electroculture to Plasma Agriculture: A Three-Century Arc Bridging Bertholon's Legacy with Contemporary Farming Advances
Announce Type: new Abstract: This review traces the historical trajectory of electricity in agriculture, from the earliest observations of electrical phenomena to the emergence of cold plasmas. Looking back to Antiquity and then to the Enlightenment, it underlines Abb\'e Bertholon's 18th-century efforts to channel atmospheric electricity to stimulate crops, using devices such as the electro-v\'eg\'etom\`etre. Although these early electroculture experiments relied on neither quantitative...
Towards A Generative Protein Evolution Machine with DPLM-Evo
arXiv:2605.00182v3 Announce Type: replace Abstract: Proteins are shaped by gradual evolution under biophysical and functional constraints. Protein language models learn rich evolutionary constraints from large-scale sequences, and discrete diffusion-based protein language models~(\eg, DPLMs) are promising for both understanding and generation. However, existing DPLMs typically rely on masked diffusion that contradicts a simple biological intuition: proteins evolve through accumulated edits,...
Human-Like Neural Nets by Catapulting
Human-like Neural Nets by Catapulting Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparameterized NNs to trigger catapulting/grokking. Over-parameterization as a route to true generalization would resolve many outstanding mysteries of artificial versus natural intelligence. There are many mysteries about deep learning and human intelligence, but we could describe the biggest anomaly this way: why are...
Amplified Arctic iceberg traffic reshapes benthic biodiversity
Abstract The Arctic is undergoing rapid warming, resulting in retreating sea ice and glaciers1, yet how cryospheric changes propagate into the deep ocean remains poorly understood2. Here we identify a climate-driven mechanism linking accelerating glacier disintegration to an increase in deep-sea hard-bottom habitats far beyond calving fronts. Seafloor observations in Fram Strait show a localized increase in the density and patchiness of dropstones delivered by debris-laden icebergs.
A Unifying View of Anchoring via Operator-Side Tikhonov Regularization
Announce Type: cross Abstract: Anchored fixed point and monotone equation methods, including Halpern iteration, extra anchored gradient, and their relatives, add a vanishing pull toward a reference point to obtain last-iterate guarantees. Existing anchored variants often achieve sharp last-iterate guarantees, but from the update-level perspective the placement of the anchor can be algorithm-specific and conceptually opaque. We show that anchoring admits a single operator-side construction:...
Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
arXiv:2606.02313v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models offer a promising end-to-end paradigm for unmanned aerial vehicles (UAVs) to accomplish complex tasks specified by fine-grained instructions. However, standard supervised fine-tuning (SFT) suffers from data scarcity, limited generalization, and weak supervision for nuanced and complicated human intents.