ReaderLM-v2: Small Language Model for HTML to Markdown and JSON

Kavli Affiliate: Feng Wang | First 5 Authors: Feng Wang, Zesheng Shi, Bo Wang, Nan Wang, Han Xiao | Summary: We present ReaderLM-v2, a compact 1.5 billion parameter language model designed for efficient web content extraction. Our model processes documents up to 512K tokens, transforming messy HTML into clean Markdown or JSON formats with high […]


Continue.. ReaderLM-v2: Small Language Model for HTML to Markdown and JSON

Collective Neutrino Oscillations in Three Flavors on Qubit and Qutrit Processors

Kavli Affiliate: Irfan Siddiqi | First 5 Authors: Luca Spagnoli, Noah Goss, Alessandro Roggero, Ermal Rrapaj, Michael J. Cervia | Summary: Collective neutrino flavor oscillations are of primary importance in understanding the dynamic evolution of core-collapse supernovae and subsequent terrestrial detection, but also among the most challenging aspects of numerical simulations. This situation is complicated […]


Continue.. Collective Neutrino Oscillations in Three Flavors on Qubit and Qutrit Processors

Collective Neutrino Oscillations in Three Flavors on Qubit and Qutrit Processors

Kavli Affiliate: Irfan Siddiqi | First 5 Authors: Luca Spagnoli, Noah Goss, Alessandro Roggero, Ermal Rrapaj, Michael J. Cervia | Summary: Collective neutrino flavor oscillations are of primary importance in understanding the dynamic evolution of core-collapse supernovae and subsequent terrestrial detection, but also among the most challenging aspects of numerical simulations. This situation is complicated […]


Continue.. Collective Neutrino Oscillations in Three Flavors on Qubit and Qutrit Processors

Large Language Models Are Innate Crystal Structure Generators

Kavli Affiliate: Kristin A. Persson | First 5 Authors: Jingru Gan, Peichen Zhong, Yuanqi Du, Yanqiao Zhu, Chenru Duan | Summary: Crystal structure generation is fundamental to materials discovery, enabling the prediction of novel materials with desired properties. While existing approaches leverage Large Language Models (LLMs) through extensive fine-tuning on materials databases, we show that […]


Continue.. Large Language Models Are Innate Crystal Structure Generators

Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing

Kavli Affiliate: Xiang Zhang | First 5 Authors: Juntai Cao, Xiang Zhang, Raymond Li, Chuyuan Li, Shafiq Joty | Summary: Recent advances in test-time scaling have shown promising results in improving Large Language Models (LLMs) performance through strategic computation allocation during inference. While this approach has demonstrated strong performance improvements in logical and mathematical reasoning […]


Continue.. Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing

A convoy of magnetic millirobots transports endoscopic instruments for minimally-invasive surgery

Kavli Affiliate: Felix Fischer | First 5 Authors: Moonkwang Jeon, Xiangzhou Tan, Felix Fischer, Tian Qiu, | Summary: Small-scale robots offer significant potential in minimally-invasive medical procedures. Due to the nature of soft biological tissues, however, robots are exposed to complex environments with various challenges in locomotion, which is essential to overcome for useful medical […]


Continue.. A convoy of magnetic millirobots transports endoscopic instruments for minimally-invasive surgery

Orbital Wigner functions and quantum transport in multiband systems

Kavli Affiliate: Joel E. Moore | First 5 Authors: Johannes Mitscherling, Dan S. Borgnia, SuryaNeil Ahuja, Joel E. Moore, Vir B. Bulchandani | Summary: Traditional theories of electron transport in crystals are based on the Boltzmann equation and do not capture physics arising from quantum coherence. We introduce a transport formalism based on ”orbital Wigner […]


Continue.. Orbital Wigner functions and quantum transport in multiband systems

Bright hybrid excitons in molecularly tunable bilayer crystals

Kavli Affiliate: Jeffrey B. Neaton | First 5 Authors: Tomojit Chowdhury, Aurélie Champagne, Patrick Knüppel, Zehra Naqvi, Ariana Ray | Summary: Bilayer crystals, built by stacking crystalline monolayers, generate interlayer potentials that govern excitonic phenomena but are constrained by fixed covalent lattices and orientations. Replacing one layer with an atomically thin molecular crystal overcomes this […]


Continue.. Bright hybrid excitons in molecularly tunable bilayer crystals

High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion

Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiang Zhang, Yang Zhang, Lukas Mehl, Markus Gross, Christopher Schroers | Summary: Despite recent advances in Novel View Synthesis (NVS), generating high-fidelity views from single or sparse observations remains a significant challenge. Existing splatting-based approaches often produce distorted geometry due to splatting errors. While diffusion-based methods leverage […]


Continue.. High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion

LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models

Kavli Affiliate: Xiang Zhang | First 5 Authors: Zongyu Wu, Yuwei Niu, Hongcheng Gao, Minhua Lin, Zhiwei Zhang | Summary: Large Vision-Language Models (LVLMs) have shown impressive performance in various tasks. However, LVLMs suffer from hallucination, which hinders their adoption in the real world. Existing studies emphasized that the strong language priors of LVLMs can […]


Continue.. LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models