D Liu

Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation

Hong Chen, D Liu, Zehan Zhang, Hao Wang et autres

Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis. This approach suffers from candidate dependence, heavy computational overhead, and inconsistencies between sampled actions and predicted visuals. To address these issues, we propose SWAM …

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Lei Bai, Zongsheng Cao, Yang Chen, Zhiyao Cui et autres

We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure …

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

Haisen Luo, Yiwei Liu, Haoning Wang, D Liu et autres

Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distillation and reinforcement learning methods lack explicit mechanisms for tracking problem-level learning progress and adapting optimization strategies accordingly. Consequently, training may …

us, fr, cn (code pays fourni par la source)

Elemental Abundances from Off-center Carbon Burning in Accreting CO White Dwarfs: Implications for SN 2021yfj-like events

Chengyuan Wu, D Liu, T J Moriya, Z LIU et autres

SN 2021yfj is a recently discovered interacting supernova that exhibits narrow emission lines of Si, S, and Ar, indicating the presence of circumstellar material (CSM) enriched with these elements surrounding the progenitor prior to the explosion. The origin of SN 2021yfj-like events …

cn, au (code pays fourni par la source)

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, Weiming Wu et autres

Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, …

Mapping the Milky Way with Masers

Yan Xu, Kazi Rygl, Huib Jan van Langevelde, D Liu et autres

SKA-VLBI is poised to revolutionize our understanding of the Galactic structure through its unprecedented astrometric precision and sensitivity. As a next-generation facility, it will answer long-standing questions about the Galactic structure by mapping its entire spiral structure in detail, spanning from the …

cn, it, nl, au, es, se (code pays fourni par la source)

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

Oxygen AIIC, Chan Long, Chao Liu, Chaofan Chen et autres

JD$.$com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, …

Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention

Xiao Li, Chengruidong Zhang, Hao Luo, Xi Lin et autres

Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active correction is still anchored to that same write address. As a result, stale information stored at a …

cn (code pays fourni par la source)

Supernova remnants in the new radio astronomy era

A. Ingallinera, M. Arias, G. Castelletti, C. Bordiu et autres

Supernova remnants (SNRs) are what is left after stellar explosions, when the stellar ejecta, the explosion shock and the circumstellar medium interact. Despite being among the first objects studied in radio astronomy, observational difficulties have so far prevented a definitive characterisation, which …

it, es, ar, fr, au, cn, ua, ca, de (code pays fourni par la source)

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Binghai Wang, Chenlong Zhang, D Liu, Jiajun Zhang et autres

A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop stronger reasoning capabilities and engineering harnesses grow more sophisticated, generating complex candidate solutions is no longer …

Extreme PeV accelerator associated with GRS 1915+105

Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao et autres

Microquasars, binary systems featuring relativistic jets, have emerged as sources for particle acceleration beyond PeV energies. We present a study of the broadband $γ$-ray emission from one of the most prominent Galactic microquasars GRS 1915+105 based on data accumulated by LHAASO and …

cn, kp, fr, ru, by, hk, no (code pays fourni par la source)

Multigrid Training for Molecular Generation using Graph Neural Networks

Zixuan Ling, Paula Mercurio, D Liu

Deep learning has demonstrated significant success for modeling biochemical molecular systems, where inputs are commonly represented as graphs or 3D grids. A major challenge is that computational cost scales with resolution, making full graph/grid computation of molecular densities expensive and often unstable. …