·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Anthropic gets its first court win over the Pentagon’s supply chain risk label1h◆Meta executive leaves for OpenAI as the social media giant faces growing scrutiny in India1h◆TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction9h◆Data-driven Koopman mode approximation: A neural power iteration algorithm9h◆Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum9h◆You Don't Need to Run Every Eval9h◆Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating9h◆Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement9h◆Provable one-poison backdoor attacks on linear models and ReLU neural networks9h◆Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments9h◆RTNav: Towards Real-Time Zero-Shot Object Navigation9h◆Magnon-induced phononic Chern insulator9h◆LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?9h◆Five Primitives for Governing Autonomous AI Agents at Runtime9h◆Privacy Without Regret: Differentially Private Inference-Time Alignment9h◆AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design9h◆GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding9h◆Categorizer Automata for Discounted-Sum Payoffs9h◆Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay9h◆Syntax vs. Semantics: How Transformers Learn Deep Dependencies9h◆Anthropic gets its first court win over the Pentagon’s supply chain risk label1h◆Meta executive leaves for OpenAI as the social media giant faces growing scrutiny in India1h◆TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction9h◆Data-driven Koopman mode approximation: A neural power iteration algorithm9h◆Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum9h◆You Don't Need to Run Every Eval9h◆Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating9h◆Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement9h◆Provable one-poison backdoor attacks on linear models and ReLU neural networks9h◆Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments9h◆RTNav: Towards Real-Time Zero-Shot Object Navigation9h◆Magnon-induced phononic Chern insulator9h◆LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?9h◆Five Primitives for Governing Autonomous AI Agents at Runtime9h◆Privacy Without Regret: Differentially Private Inference-Time Alignment9h◆AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design9h◆GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding9h◆Categorizer Automata for Discounted-Sum Payoffs9h◆Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay9h◆Syntax vs. Semantics: How Transformers Learn Deep Dependencies9h◆
News/MDTransformer: A Hardware-Software Co-Design of Mode-Division Photonic Transformer Accelerator with Inverse-Designed Coherent Crossbar
arxiv
PublishedJuly 29, 2026 at 4:00 AM

MDTransformer: A Hardware-Software Co-Design of Mode-Division Photonic Transformer Accelerator with Inverse-Designed Coherent Crossbar

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2607.26016v1 Announce Type: cross Abstract: Recently, photonic transformer accelerators (PTAs) have successfully achieved significant speedup and energy efficiency improvements over electronic accelerators for expediting Transformer inference. However, state-of-the-art rely on expensive multi-

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivTRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction9harxivData-driven Koopman mode approximation: A neural power iteration algorithm9harxivLearning to Reason with Curriculum I: Provable Benefits of Autocurriculum9harxivYou Don't Need to Run Every Eval9h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews