Good Papers

Showing papers from Nankai University Show all papers

72%Highly rated
?Highly ratedVote to see the score
arXivThe University of Texas at AustiZhejiangHong Kong PolytechnicU Science and Technology of ChinBeijing University of Posts and LLM reasoning & chain of thought

On the Geometry of On-Policy Distillation

On-policy distillation updates occupy a sparse, low-dimensional parameter subspace that is functionally sufficient and geometrically distinct from supervised fine-tuning and reinforcement learning.

Zhennan Shen, Yanshu Li, Qingyu Yin, Chak Tou Leong and 5 more

Published Jun 5, 2026 · 0 citations · ▲ 75 on Hugging Face

– ReadersNo votes yet. 1 from authors or colleagues not counted
8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 8 of 20 reviewers recommend it
lenient 3/5
medium 4/10
strict 1/5
59%Worth a look
?Worth a lookVote to see the score
KDD 2026NankaiBeihangGraph transformers

Invariant Graph Transformer for Out-of-Distribution Generalization

GOODFormer improves graph transformer out-of-distribution generalization by jointly learning invariant predictive subgraphs, evolving positional encodings, and invariant representations.

Tianyin Liao, Ziwei Zhang, Yufei Sun, Chunyu Hu and 1 more

Published Apr 20, 2026 · 0 citations

0% Readers0 of 1 upvoted
7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 7 of 20 reviewers recommend it
lenient 2/5
medium 5/10
strict 0/5
80%Must read
?Must readVote to see the score
U Notre DameWashington University in St. LouPurdue University West LafayetteU Illinois Urbana-ChampaignNankaiInstruction tuning

From Personal to Collective: On the Role of Local and Global Knowledge in LLM Personalization

LoGo augments individual user signals with evolving global and community-level behavioral patterns via adaptive mediation, improving LLM personalization and reducing overfitting.

Zehong Wang, Junlin Wu, Zhaoxuan Tan, Bolian Li and 3 more

Published 2026 · 0 citations

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026NankaiTianjinFederated learning

Confounding-Aware Client Selection in Federated Learning via Causal Mediation Analysis

Xiaoyang Yi, Yuru Bao, Rihao Chang, Binhan Yang and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SJTUNankaiAlibaba GroupBeihangShanghai JiaotongDiffusion models

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

Zhengrong Yue, Taihang Hu, Mengting Chen, Haiyu Zhang and 7 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026FudanU Hong KongShanghai JiaotongXi'an JiaotongNankaiVision-language models

MedVTok: A General-Purpose Medical Visual Tokenizer

Chenglong Ma, Yuanfeng Ji, Junzhi Ning, Jiyao Liu and 17 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Xi'an JiaotongNankaiShanghai JiaotongShanghai Jiao TongVision-language-action models

TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation

Zhihong Liu, Yang Li, RenMing Huang, Chendong Zeng and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Nanjing University of Science anNankaiNanjing University / RIKENNanjingDiffusion models

Beyond Generation: Unlocking Discriminative Representations from Diffusion Models

Haowen Cui, Ge Wu, Shuo Chen, Yikai Ge and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Science and Technology of ChinU California, BerkeleyShanghai JiaotongNankaiCOWAROBOT3D generation

LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance

Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Qifeng Li and 9 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Institute of automation, ChineseNankaiZhejiangU the Chinese Academy of ScienceInstitute of automation, ChineseLLM evaluation & benchmarks

SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models

Senhao Yang, Ziling Yuan, Xiaoran Yang, Yaqing Wang and 6 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Shanghai JiaotongXiamenDalian University of TechnologyNankaiHarbin EngineeringAgent benchmarks & environments

PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design

Fuyuan Xia, Jiaxin Hu, Kewei Yu, Zihan Zhang and 12 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NanKaiNankaiShandong JianzhuJilinHarbin Institute of TechnologyVision-language models

Counterfactual Instruction Grounding for Vision-Language-Action Models

Shiyu Liu, Yu Zhou, Meng Liu, Xuanming Guo and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NankaiTsinghuaHuazhong University of Science aU the Chinese Academy of SciencevivoAgent memory

PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents

Jian Zhong, Zeyu Liu, Pingchuan Cao, Rongduo Han and 7 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026TsinghuaTsinghua University, TsinghuaNankaiBeijing UnionAlibaba GroupDeep RL

Feasible Policy Optimization for Safe Reinforcement Learning

Yujie Yang, Yuanxu Sun, Wenyu Li, Beiyan Jiang and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NankaiShanghai JiaotongSemi- & weakly supervised learning

Resilient Semi-Supervised Inference with Heterogeneous Unlabeled Data

Mengyuan Wang, Chengde Qian, Haojie Ren, Changliang Zou

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SpotlightNankaiNankai University Nanjing University of Science anNanjingSegmentation

MonoChunk3D: Monocular Online 3D Instance Segmentation with Persistent Instance States

Yibo Zhao, Jingzhi Zhou, Yigong Zhang, Jian Yang and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Civil Aviation University of ChiNankai3D vision & reconstruction

SynGS: Synergistic Continual Learning and Change Detection with Gaussian Splatting

Rui Huang, Haojie Tao, Sen Gao, Qing Guo

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026FudanNankaiOffline RL

Post-Selection-Safe Pessimistic Utilities for Offline Multi-Objective Reinforcement Learning

Mingxi Hu, Meiling Yu

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NankaiAlibaba GroupAnt GroupRenmin University of ChinaDiffusion models

Diffusion Transformers with Residual Adaptive Layer Normalization

Ge Wu, Minxing Luo, Yikai Ge, Lei Wang and 7 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Computer Vision Center, UniversiUniversitat Autónoma de BarcelonNankaiComputer Vision Center BarcelonaCity University of Hong Kong3D generation

DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization

Tao Wu, Alexandra Gomez-Villa, Senmao Li, Yaxing Wang and 2 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026NankaiThe Hong Kong University of ScieHKUSTZhejiangHong Kong University of Science Test-time compute

SIGMA: A Sigmoid-Gated Sampler for Test-Time Scaling in Diffusion Language Models

Ziwen Zhang, Weiyu Chen, Yuyan Zhou, Yichen Zhu and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Kuaishou- 快手科技national university of singaore,NankaiKuaiShou TechnologyKuaishou TechnologyVision-language models

Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval

Yufei Ma, Zihan Liang, Zhipeng Qian, Huangyu Dai and 4 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026NankaiAlibaba GroupSJTUAlibaba Inc.Diffusion models

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Continuous-Time Distribution Matching replaces discrete step anchoring with continuous distribution optimization and off-trajectory alignment to accelerate diffusion models without auxiliary networks. CDM achieves competitive few-step image generation fidelity across architectures without GANs or re

Tao Liu, Hao Yan, Mengting Chen, Taihang Hu and 7 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026 · ▲ 27 on Hugging Face · Code ★ 154

– ReadersNo votes yet
8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 8 of 20 reviewers recommend it
lenient 3/5
medium 5/10
strict 0/5
71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026NankaiZhejiangSouthern University of Science aRightly RoboticsU Science and Technology of Chin3D vision & reconstruction

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos

DeformMaster learns interactive physics-neural world models of deformable objects from videos, enabling high-fidelity future dynamics rollout, material variation, and novel-view synthesis.

Can Li, Zhoujian Li, Ren Li, Jie Gu and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 25

– ReadersNo votes yet
7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 7 of 20 reviewers recommend it
lenient 3/5
medium 3/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026NankaiBeijing Institute of TechnologyHarbin Institute of Technology, Renmin University of ChinaMicrosoft Research AisaRL for LLMs

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training

SCOPE-RL uses temperature-adaptive positive samples to stabilize entropy and prevent collapse in RL post-training of reasoning LLMs, improving Pass@1 and Pass@$k$ with non-monotonic exploration benefits.

Chen Wang, Zhaochun Li, Bai Jionghao, Hexuan Deng and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 1/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026SpotlightNankaiMonashShanghai JiaotongFudanShanghai Jiao TongLLM evaluation & benchmarks

IndustryCode: A Benchmark for Industry Code Generation

IndustryCode is a multi-domain, multi-language benchmark of 579 industrial coding sub-problems; Claude 3.5 Opus reaches 68.1% sub-problem and 42.5% main-problem accuracy.

Puyu Zeng, Zhaoxi Wang, Zhixu Duan, Liang Feng and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 5/10
strict 1/5
80%Must read
?Must readVote to see the score
NeurIPS 2026U Science and Technology of ChinTencentZhejiangSchool of data science, Fudan unNankaiTokenization

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

SimCT recovers lost cross-tokenizer supervision by comparing multi-token continuations in on-policy distillation, improving reasoning and code generation over exact token matching.

Jie Sun, Mao Zheng, Mingyang Song, Qiyong Zhong and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 4/5
medium 8/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026TsinghuaNankaiCanvaObject detection

Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection

DAD treats graphic design detection as ordered compositional deconstruction with amodal bounding boxes and element-level reinforcement learning, achieving human-level amodal detection and outperforming baselines across nine benchmarks.

Jiangning Zhu, Bowen Li, Shenyu Qiao, Yima Gu and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 5/10
strict 1/5
83%Must read
?Must readVote to see the score
NeurIPS 2026JD.comU the Chinese Academy of ScienceJD.COMNankaiU the Chinese Academy of ScienceInstruction tuning

The Hidden Power of Scaling Factor in LoRA Optimization

LoRA's scaling factor dominates optimization by amplifying task signals without increasing drift, outperforming learning rate adjustments. The optimal alpha follows a sublinear square-root law with rank, revealing insufficient scaling in existing heuristics. Proposed LoRA-alpha restores principled s

Zicheng Zhang, Haoran Li, Jiaxing Wang, Guoqiang Gong and 9 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 12 on Hugging Face

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 3/5
medium 8/10
strict 2/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Kuaishou- 快手科技NankaiU Pennsylvania, University of PeKuaiShou TechnologyLLM agents & planning

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations

Bian Que is an agentic framework that arranges flexible skills for online system operations, reducing alerts by 75% and cutting resolution time by over 50%.

bochao liu, Zhipeng Qian, yang zhao, Xinyuan Jiang and 8 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026U the Chinese Academy of ScienceTsinghuaTencent HYInstitute of Information EngineeNankaiVisual grounding

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding

GUI-SD uses on-policy self-distillation with privileged visual contexts and entropy-guided distillation for GUI grounding, outperforming GRPO methods in accuracy and efficiency.

Yan Zhang, Daiqing Wu, Huawen Shen, Can Ma and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 5 on Hugging Face

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U the Chinese Academy of ScienceNankaiGuizhou Power Grid Co., Ltd.Institute of Software, Chinese AInstitute of Software Chinese AcTime series forecasting

Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting

Dirichlet-Guided Group Forecasting reduces time-series over-smoothing by modeling multi-modal predictive distributions with Dirichlet-guided sampling, improving accuracy, diversity, and dynamical consistency.

Xingyu Zhang, Jingyao Wang, Xin Yu, Zeen Song and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 11 of 20 reviewers recommend it
lenient 4/5
medium 7/10
strict 0/5
89%Must read
?Must readVote to see the score
NeurIPS 2026NankaiTsinghuaCanvaDiffusion models

PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining

PixelART trains a pixel-space diffusion transformer from scratch to decompose images into editable RGBA layers, achieving state-of-the-art results with 80% fewer parameters and 98% lower latency than pretrained alternatives.

Zelin Jia, Zhao Zhang, Zhicong Tang, Yuhui Yuan and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 16 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 2/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026NankaiShandong JianzhuEmbodied agents

RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation

RAO-Nav applies omni-language models to zero-shot audio-visual navigation via a reasoning pipeline with latent navigation reasoning, surpassing trained state-of-the-art baselines without training data.

Qilang Ye, Meng Liu, Yu Zhou

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 3/5
medium 6/10
strict 1/5