STS
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation
Announce Type: new Abstract: A common intuition is that sentence embeddings should adapt to the difficulty of the input. We test this intuition in a controlled, multi-seed setting: a lightweight post-encoder adapter attaches to a frozen Qwen3-Embedding-0.6B encoder, accessing only its final pooled embedding, and is evaluated on four paraphrase and semantic-similarity tasks (PAWS, MRPC, QQP, STS-B). The naive form of the idea fails: surface-based per-sentence complexity is nearly uncorrelated...
Strategic Type Spaces
arXiv:2606.08297v1 Announce Type: cross Abstract: We provide a strategic foundation for information: in any given game with incomplete information we define strategic quotients as information representations that are sufficient for players to compute best-responses to other players. We prove 1/ existence and essential uniqueness of a minimal strategic quotient called the Strategic Type Space (STS) in which a type is given by an interim correlated rationalizability hierarchy and represents a...
A Cartesian-3j Framework for Machine Learning Interatomic Potentials
Announce Type: replace-cross Abstract: Machine learning interatomic potentials (MLIPs) have brought substantial gains in the extrapolation capability in computational chemistry. However, most equivariant models are typically built with spherical tensors (STs), while Cartesian tensor formulations remain less developed despite their natural alignment with atomic coordinates and tensorial targets. In this work, we develop a Cartesian framework for irreducible Cartesian tensors (ICTs) by...
A Cartesian-3j Framework for Machine Learning Interatomic Potentials
Announce Type: replace Abstract: Machine learning interatomic potentials (MLIPs) have brought substantial gains in the extrapolation capability in computational chemistry. However, most equivariant models are typically built with spherical tensors (STs), while Cartesian tensor formulations remain less developed despite their natural alignment with atomic coordinates and tensorial targets. In this work, we develop a Cartesian framework for irreducible Cartesian tensors (ICTs) by introduce the...
When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics
arXiv:2606.03569v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores. This single-metric paradigm presents a critical flaw: high attention scores inherently collapse onto semantically similar regions, thereby severely reducing feature diversity and...
Happy Pride Month! Remembering Sally Ride's historic legacy | Space photo of the day for June 3, 2026
Remembering Sally Ride's historic legacy | Space photo of the day for June 3, 2026 In June 1983, Sally Ride became the first American woman to fly to space. Nearly three decades later, we learned that she had also been an LGBTQ trailblazer. In June of 1983, Sally Ride became the first American woman to fly to space.
From 'Tetris' to 'StarCraft 2' — 5 times astronauts took video games into space
From 'Tetris' to 'StarCraft 2' — 5 times astronauts took video games into space How would you like to play a game ... in spaaaaaaccccceeeeeee!!!! Video games have come a long way since their inception, but you’ll find the furthest they’ve gone (so far) is the depths of space itself. No, we're not talking about video games set in space; these actually went into space.
Could meteor storms harm NASA's future moon missions?
Could meteor storms harm NASA's future moon missions? "If a major meteor shower outburst or storm is forecast during a mission or crew activity, the mission would be delayed or the crew kept inside until the outburst or storm is over." Meteor showers are among the most beautiful phenomena to brighten Earth's sky, but could the fast moving space rocks that accompany major events threaten or delay future Artemis moon missions as NASA and its partners plan for a lunar landing attempt?
Can Data Work be Reparative?
arXiv:2606.09408v1 Announce Type: new Abstract: We present an ethnographic study of an alternative approach to data work, developed by a civic-tech initiative that builds datasets for training and benchmarking online safety systems. They aim to respond to online safety concerns from a feminist perspective, by building safety datasets collaboratively with those most impacted by online harms. In this paper, we examine how this approach aims to reorient data work as a site for repair and...
Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning
arXiv:2606.05173v1 Announce Type: new Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure. Inspired by the success of Joint Embedding Predictive Architectures (JEPA) (LeCun, 2022) in vision and audio, we propose a hybrid pre-training objective that combines a JEPA-style latent-space prediction loss...