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.
[PDF]EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning OptimizationChung-Yiu Yau, Dawei Li, Athanasios Glentis et al.4.33
[PDF]Reading Between the Dots: Decoding Hidden Computation across Filler TokensKaley Brauer, Claudio Mayrink Verdun, Samuel Marks4.33
[PDF]Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair SupervisionJiacheng Chen, Songze Li, Han Fu et al.4.33
[abs]MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed RecognitionYuyang Sun, Senyang Su, Xiaotian Wang et al.4.33
[PDF]S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance SegmentationLeon Sick, Lukas Hoyer, Dominik Engel et al.4.33
[PDF]Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement LearningHannes M Büchi, Manon Flageat, Eduardo Sebastián et al.4.33
[abs]HyperNSDE: Personalized Neural SDEs for Joint Static—Longitudinal Clinical Data GenerationPerrine Chassat, Agathe Guilloux4.33
[PDF]FlashMol: High-Quality Molecule Generation in as Few as Four StepsXinyuan Wei, Zian Li, Shaoheng Yan et al.4.33
[abs]Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth PromptsKun Wang, Yun Zhu, Pan Zhou et al.4.33
[PDF]Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language ModelsLin Zheng, Vasilisa Bashlovkina, Timothy Dozat et al.4.33
[PDF]Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMsHoigi Seo, Byung Hyun Lee, Minjun Kim et al.4.33
[abs]Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT DistillationYongcan Yu, Jian Liang, Lingxiao He et al.4.33
[PDF]Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video GenerationHanlin Chen, Jiaxin Wei, Xibin Song et al.4.33
[PDF]Metaphor Is Not All Attention NeedsOlga Sorokoletova, Francesco Giarrusso, Giacomo De Luca et al.4.33
[abs]BlockFormer: Transformer-based inference from interaction mapsEloïse Touron, Pedro Rodrigues, Julyan Arbel et al.4.33
[PDF]Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal ReasoningWenxi Gao, Guanxi Lu, Didi Zhu et al.4.33
[abs]FedSOUL: Federated Continual Unlearning via Spectral OrthogonalityHaoran Shi, Hao Zhu, Yifei Zhang et al.4.33
[abs]Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMsSongming Yang, Hong-Tao Yu, Xiu-Shen Wei4.33
[PDF]Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLMWenqian Cui, Xiao-Hui Li, Daxin Tan et al.4.33
[abs]MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout ReconstructionYuguang Li, Yichuan (Ethan) Deng, Zixuan Liu et al.4.33
[PDF]NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-ResolutionXiangtao Kong, Rongyuan Wu, Shuaizheng Liu et al.4.33
[PDF]Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual EmbeddingsShubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja4.33
[PDF]Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling FailuresLinhai Zhang, Yulan He4.33
[abs]Gradient-Free Editing for Attribute Invariance in Graph Neural NetworksAastha A K Verma, Vishakha Agarwal, Sahil Manchanda et al.4.33
[PDF]Human-AI Teaming Through the Lens of CalibrationEric Nalisnick, Chi Zhang, Chengxin Qian et al.4.33
[abs]LaSA-Net: A Language-Guided Network for Outdoor Generalized 3D Referring Expression SegmentationLingfei Ma, Bin Liu, Wen Li et al.4.33
[PDF]The Hidden Power of Scaling Factor in LoRA OptimizationZicheng Zhang, Haoran Li, Jiaxing Wang et al.4.33
[abs]PuppetGait: Generalizing Gait Recognition via 3D Body-Aligned LVM Features成伟 叶, Dingqiang Ye, Chuanfu Shen et al.4.33
[abs]Online Maximization of Non-Decomposable Test and Population UtilitiesWojciech Kotlowski, Marek Wydmuch, Krzysztof Dembczynski4.33
[abs]Energy-Based Operator Learning in Function SpaceHong Chul Nam, Jeonghwan Cheon, Jae Mo Shin et al.4.33
[abs]AgenTracer-v2: Agentic Failure Tracer for LLM Agentic SystemsGuibin Zhang, Haoyu Lu, Junhao Wang et al.4.33
[abs]Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream AdaptationMin-Seong Kim, Jongbok Won, Jeesup Park et al.4.33
[abs]Breaking Adversarial Transferability in Fine-Tuned Speech RecognitionMojtaba Nafez, Aref Mousavi, Mohammad E Mahdavi et al.4.33
[abs]PhaseDance: Capturing Rhythm and Expressivity in Dance ModelingMeongeun Kim, Taehui Lee, Soomin Park et al.4.33
[abs]PM-LoRA: Scalable Continual Learning via Progressive Merging of Low Rank AdaptersXiaobing Yu, Peijie Qiu, Jin Yang et al.4.33
[abs]Elephant in the Fridge: Constant-Memory Frame Packing for Long Video UnderstandingShuo Gao, Chenhao Zheng, Jason Ren4.33
[PDF]From Perception to Punchline: Empowering VLM with the Art of In-the-wild MemesXueyan Li, Yingyi Xue, Mengjie Jiang et al.4.33
[abs]Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory AttributionZhenshuo Zhang, Ruoxuan Xiong, Hongyang Zhang4.33
[PDF]TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce RetrievalXinyu Sun, Huangyu Dai, Lingtao Mao et al.4.33
[PDF]Leveraging unlabelled data for generalizable neural population decodingXimeng Mao, Nanda H Krishna, Hee-Woon Ryoo et al.4.33
[abs]The limbic navigation system as a hierarchical RNNZilong Ji, Huiwen Zhang, Krishna Gorantla et al.4.33
[PDF]Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RLSophia Xiao Pu, Zhaotian Weng, Chengzhi Liu et al.4.33
[PDF]TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool CompositionAnay Kulkarni, Chia En Lu, Dheeraj Mekala et al.4.33
[abs]Hierarchical Agglomerative Clustering via Relaxed RepresentativesEduardo Laber, Miguel A Batista4.33
[abs]Reasoning-based Spatial Prior (RSP): Learning Spatial Priors from Multimodal LLMs for Object DetectionCagri Gungor, Qingshuang Chen, Hongda Mao et al.4.33
[abs]Attending on Attention (): Smaller Self-Supervised ViTs Localize Better Than Larger OnesSreehari Rammohan, Huy Ha, Carl Vondrick4.33
1 If this project is interesting to you, reach out at [email protected].