works on

From the 1 of 10 linked papers with an AI index.

collaborators

10 papers

cs.CV2026

XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling

Jinxiu Liu, Xuanming Liu, Kangfu Mei +2

High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient method…

cs.CV2026

SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning

Jinxiu Liu, Jianru Li, Tanqing Kuang +4

The paper introduces SymbOmni, an agentic omni-model for visual generation that uses a symbolic concept memory to continuously learn and compose reusable instructions, enabling con…

cs.AI2026

Beyond the Sampled Token: Preserving Candidate Support in RLVR

Ruotian Peng, Yi Ren, Zhouliang Yu +2

We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the \emph{candidate distribution} for next-token prediction. We fo…

cs.LG2026

Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

Yuhuan Yuan, Zhouliang Yu, Minghao Liu +2

LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility. We identify a data-induced failure mode, PhysHack, in which the assemblies satisfy phy…

cs.LG2026

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective

Yangyi Huang, Ruotian Peng, Zeju Qiu +4

Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking t…

cs.LG2026

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

Kexuan Shi, Hanxuan Li, Zeju Qiu +3

We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additive optimizers such as Adam a…