NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of NeurIPS 2026
Abstract
The safe for work edition of acceptodds: the submissions, without the markets. Search them, browse them on a map laid out by what they are about, follow the ones you care about, keep reading lists with your group, and get recommendations from what you read. There are no odds, no bets and no reputation here. acceptodds is not affiliated with any organisation or institution. acceptodds is an open source project, open to contributions, at github.com/PotentialHedge/acceptodds-sfw.1 Follow for updates on X.
[abs]Structural Self-Teaching for Compositional Generation in Unified Multimodal ModelsJaeyoo Park, Bohyung Han4.33
[abs]Towards Better Generalization in Lifelong Person Re-Identification with Flatness-Aware LearningSeungbin Hong, Sung Whan Yoon, Jae-Young Sim4.33
[abs]SAGE: Evidence-First Biomarker Discovery through Multi-Agent ReasoningSahar Almahfouz Nasser, Juan Francisco Pesantez Borja, Jincheng Liu et al.4.33
[abs]Sequential Probability Assignment against Smoothed Adversaries with Unknown Base MeasureZiyi Liu, Dan Roy4.33
[PDF]Short-Context Dominance: How Much Local Context Natural Language Actually Needs?Vala Vakilian, Zimeng Wang, Ankit Rawat et al.4.33
[abs]U-MVP: Encode Locally, Decode Globally for Feed-Forward 3D Gaussian SplattingSeungkwon Yang, Gyeongjin Kang, Hwasik Jeong et al.4.33
[abs]LDM-is-AE: Latent Diffusion is an Intrinsic Auto-Encoder for End-to-End Image GenerationZhengqiang ZHANG, Lingchen Sun, Rongyuan Wu et al.4.33
[abs]VLS: A Vision-Language-Shape Model for Open-Vocabulary Partonomic 3D ReconstructionXiaoqian Ruan, Pei Yu, Dian Jia et al.4.33
[PDF]PISCO: Precise Video Instance Insertion with Sparse ControlXiangbo Gao, Renjie Li, Xinghao Chen et al.4.33
[PDF]Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic CritiqueSanidhya Vijayvargiya, Rahul Lokesh4.33
[abs]Endowing Your Vision-Language-Action Model with a Predictive MindPengxiang Ding, Haoying Wang, Minghui Lin et al.4.33
[abs]Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM InferenceZhichen Zeng, Xichong zhang, Junpan Wu et al.4.33
[abs]DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D SegmentationZHIFAN ZENG, Wenbo Xiao, Arcot Sowmya et al.4.33
[PDF]Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep StagingKunmin Jang, Yourim Choi, Hun Heo et al.4.33
[PDF]Optimizing Computational-Statistical Runtime for Wasserstein Distance EstimationPeter M Jacobs, Jeff M Phillips4.33
[abs]Reading, Not Thinking: Bridging the Modality Gap When Text Becomes PixelsKaiser Sun, Xiaochuang Yuan, Hongjun Liu et al.4.33
[abs]Grounding Agent Reasoning with Structured Process Supervision for Multi-turn Reinforcement LearningRenting Rui, Yulei Qin, Weiwen Liu et al.4.33
[abs]SD-Search: Hindsight Self-Distillation for Search-Augmented ReasoningYufei Ma, Zihan Liang, Ben Chen et al.4.33
[abs]Treating Hyperparameters as Interventions: Task-Invariant Representation Learning for Transferable HPOMengyang Li, Ou Wu4.33
[PDF]COVD: Continual Open-Vocabulary Object Detection with Novel Concept InjectionYupeng Zhang, Ruize Han, Yuzhong Feng et al.4.33
[PDF]Learning to Solve Generative ODEs Beyond the Linear SpanSihyeon Kim, Seunghun Lee, Vikas Singh et al.4.33
[PDF]V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language ModelsXinying Lin, Xuyang Liu, Yiyu Wang et al.4.33
[PDF]Generative Scenario Rollouts for End-to-End Autonomous DrivingRajeev Yasarla, Deepti Hegde, Shizhong Han et al.4.33
[abs]Tio: Language Models with Parallel Streams of Thoughts, Inputs and OutputsGuinan Su, Yanwu Yang, Xueyan Li et al.4.33
[abs]IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectoriesshang xue, Li Zhu, Ping Chen4.33
[abs]Firefly: Illuminating Verified Real-world Tool Call Data GenerationYuxuan Lu, Ziyi Wang, Yingzhou Lu et al.4.33
[abs]From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representationsVezha Boboeva, Alberto Pezzotta, George Dimitriadis et al.4.33
[PDF]XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray DiffractionHanyu Gao, Bin Cao, YUNYUE SU et al.4.33
[abs]Gaeta-Lie Neural SDEs: Symmetry-Regularized Learning of Stochastic DynamicsShida Liu, Sumit Sinha, L Mahadevan4.33
[PDF]DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop ReasoningHengyu Fu, Tianyu Guo, Zixuan Wang et al.4.33
[PDF]Squeezing Capacity from Multimodal Large Language Models for Subject-driven GenerationShuhong Zheng, Aashish K Misraa, Kevin Li et al.4.33
[abs]Learning Cultural Vectors for Cross-Cultural GenerationSina Malakouti, Deepti Ghadiyaram, Boqing Gong et al.4.33
[abs]MCAS: Signal-Processing-Based Multi-View Contrastive Learning for Acoustic SensingBingzhi Wang, Jiajun Yu, Dengke Zhong et al.4.33
[PDF]AsyncOPD: How Stale Can On-Policy Distillation Be?Wonjun Kang, Kevin Galim, Seunghyuk Oh et al.4.33
[abs]Mitigating Overgeneralization in RND via Spectral Target DesignMinseok Jeong, Yechan Lee, Hyewon Choi et al.4.33
[PDF]Learning Visual Feature-Based World Models via Residual Latent ActionXinyu Zhang, Zhengtong Xu, Yutian Tao et al.4.33
[abs]Online Directional Regression for Streaming Sufficient Dimension ReductionDohyun Kim, Hyungryul Park, Kyongwon Kim4.33
[PDF]B[FM]: Brain Foundation Model via Flow Matching with SplitUNetJaedong Hwang, Kathleen Zhang, David Dai et al.4.33
[PDF]Sandboxed Coding Agents are Competitive Omni-modal Task SolversDongping Chen, Xuanao Huang, Zhihan Hu et al.4.33
[PDF]Ensembling Language Models with Sequential Monte CarloRobin Chan, Tianyu Liu, Samuel Kiegeland et al.4.33
[abs]Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual LearningKun Gu, De Cheng, Zhipeng Xu et al.4.33
[abs]Local FDR Membership Inference Attacks: Multiple Testing and the Role of Ridge RegularizationJinyoung Hong, Bonwoo Lee, Jeongyoun Ahn4.33
[PDF]Automated Reformulation of Robust Optimization via Memory-Augmented Large Language ModelsJinbiao Chen, Shuang Jin, Guoyun Zhang et al.4.33
[PDF]LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?Xueqi Cheng, Yushun Dong4.33
[PDF]Geometric Analysis of Neural Regression Collapse via Intrinsic DimensionGeorge Andriopoulos, Zixuan Dong, Bimarsha Adhikari et al.4.33
[abs]PosePlaner: Denoising Any Feedforward Pose Predictor from Pairwise Planar GeometryYihang Chen, Bin Tan, Yujun Shen et al.4.33
1 If this project is interesting to you, reach out at [email protected].