paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

NeurIPS 2026

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

Jiakang Wang, Runze Liu, Fuzheng Zhang, Xiu Li, Guorui Zhou, Kun Gai, Ling Pan

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, existing methods mainly apply uniform optimization constraints across all tokens, ignoring their heterogeneous roles. Prior work shows that high-entropy tokens are closely tied to reasoning, while low-entropy tokens primarily encode factual knowledge, and recent approaches attempt to exploit this distinction by isolating token updates via masking or asynchronous training. We argue that such isolation breaks the sequential dependency structure of autoregressive generation, leading to suboptimal learning. To address this, we propose \textbf{Archer}, an entropy-aware RLVR framework with \textbf{dual-token constraints} that preserves joint optimization while modulating update strength across token types. Our method introduces response-level entropy normalization for stable token classification and applies differentiated clipping ranges and KL regularization to encourage exploration on reasoning tokens while preserving knowledge tokens. Experiments on mathematical reasoning and code generation benchmarks show that Archer consistently outperforms strong baselines across multiple model scales, improving both \textit{pass@1} and \textit{pass@K} performance. These results highlight the importance of respecting sequence-level dependencies when designing fine-grained RL optimization strategies for LLMs.

NeurIPS 2026

Stabilizing Few-Shot Object Detection with Language-Conditioned Probabilistic Prototypes

Jiaying Wu, Yuchun Zhao, Lei Shi, Jia Luo, Dongmei Wei, Feifei Kou, Pengfei ZHANG, Zhaoman Zhong

Few-shot object detection (FSOD) requires detectors to adapt to novel categories from only a few labeled instances, where prototype-based transfer methods have become a strong and efficient paradigm. However, we observe that such methods remain unstable in extreme low-shot regimes. We attribute this instability to two coupled factors: semantically unanchored query initialization, which yields high-variance cold-start optimization, and deterministic prototype matching, which over-trusts noisy or occluded support regions. To address these limitations, we propose Semantic Fine-Grained Prototype Distillation (SFPD), a language-conditioned probabilistic adaptation framework for prototype-based FSOD. SFPD introduces language-conditioned feature queries to provide semantic anchors for novel-class adaptation, uncertainty-aware prototype distillation to down-weight unreliable support evidence through heteroscedastic Gaussian modeling, and component-guided part-aware prototypes to refine fine-grained semantic-visual alignment. These modules act during adaptation and preserve the original detector path at inference, introducing no additional inference FLOPs. Experiments on PASCAL VOC and MS-COCO show that SFPD consistently improves a strong FPD baseline, with especially clear gains in the most challenging low-shot settings, e.g., a 3.9-point nAP50 improvement on VOC Split 2 under 1-shot. Further ablations, multi-seed evaluation, and convergence analysis indicate that SFPD improves both accuracy and adaptation stability.

NeurIPS 2026

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger, Wieland Brendel, Martin Jaggi

Looped Transformers --- which repeatedly apply a shared transformer block --- are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong length generalization beyond the length of training sequences, this behavior is brittle, yielding high out-of-distribution (OOD) variance, even across well-performing in-distribution solutions. We trace this variance to the spurious correlation in simple algorithmic tasks between sequence length and number of loops. Introducing stochasticity into the number of loops during training sharply reduces OOD variance and stabilizes predictions across inference-time loop counts. To improve upon heuristic randomization schemes, we further analyze RL-Halting as a learned stochastic schedule and find that it generally improves the accuracy--stability trade-off. Across binary addition, Dyck-1, Unique Set, and Copy, learned stochastic stopping often improves this trade-off but can also stabilize a suboptimal computation. Our work suggests that “when to stop” should be treated as a training-time design choice, not merely an inference-time computation-allocation rule.

NeurIPS 2026

Stability-Weighted Direction Regularization Disentangles Generator Shortcuts from Detection Signal

Jang-Ho Choi, Seongho Kim, Jaehyun Choi, Dahye Kim, Sungwon Yi, Eunho Yang

AI-generated image detectors often generalize poorly to unseen generators because the classifier latches onto generator-specific feature directions that are predictive only on the training set. We show that simply projecting away generator-discriminative LDA directions fails: these directions also carry genuine real-vs-fake signal, so post-hoc erasure removes evidence along with shortcuts. We introduce StaR, a training-time regularizer that scores each LDA direction by leave-one-generator-out stability and penalizes the classifier only on unstable directions; stable directions are left available for classification. On ResNet-50, StaR reduces the across-seed standard deviation of the four-OOD average AUC by 24x relative to ERM (F-significant on every OOD) while preserving in-distribution-like performance; on CLIP ViT-L/14, StaR improves the four-OOD average AUC by 1.7 points over matched CLIP-ERM and 4.5 over EFFORT, with the largest gains on platform-shift benchmarks. Mechanistic analyses show that StaR rotates the classifier away from unstable generator directions while amplifying generator-discriminative structure in the features---a rotational, not erasive, effect that post-hoc projection cannot reproduce. We additionally find that the conventional ``argmax in-domain validation'' epoch-selection rule is sub-optimal: a deployable ``stop at first in-domain 0.99'' rule beats it by sim0.7 AUC points on average.

NeurIPS 2026

Stability-Enhanced Federated Learning with Accelerated Gradient

Tianxiang Chen, Wenjie Hou, Feng Wang, Tiantong Wang, Zhiming Zheng, Shaoting Tang, Wei Yang Bryan Lim

Federated Learning (FL) is a promising paradigm for distributed machine learning. However, FL often suffers from degraded generalization performance due to the inconsistency between local and global optimization objectives and client-side overfitting. In this paper, we provide a global-update stability analysis framework as an analytical tool to study generalization error and derive the stability bounds of mainstream FL optimization algorithms under non-convex settings. Our analyses reveal how the number of global update steps, data heterogeneity, and update rules influence their stability. We observe that momentum-based FL acceleration methods do not improve stability. To address this issue, we propose FedSEMA, a new FL algorithm that couples global momentum with a gradient-difference corrected Nesterov Accelerated Gradient (NAG) scheme and a hybrid proximal term to enhance stability. This design ensures updates follow a globally consistent descent direction while retaining the benefits of acceleration. Theoretical analysis shows that FedSEMA achieves an improved stability upper bound on non-i.i.d. datasets in the non-convex settings. Extensive experiments on real-world datasets demonstrate that FedSEMA significantly outperforms multiple baseline methods under standard FL settings, achieving faster convergence and state-of-the-art performance.

NeurIPS 2026

Stability-Aware Self-Training for CLIP under Cross-Modal Anchoring Mismatch

Siyuan Liu, Xinyang Chen, Xiucheng Li, Weili Guan, Liqiang Nie

Self-training is a practical way to adapt CLIP with limited supervision, but its performance is highly sensitive to pseudo-label reliability. We identify an important failure mode in CLIP adaptation: temporal prediction instability, where a target sample repeatedly flips its prediction across epochs. We provide a perspective based on cross-modal anchoring mismatch: the decision geometry induced by pretrained text anchors can deviate from the local visual cluster structure of the target domain. This mismatch can make ambiguous target samples susceptible to prediction flips during adaptation, whereas target-aligned anchoring produces more stable pseudo-labels. Motivated by this observation, we propose Stability-Aware Self-Training (SAST), centered on Stability-Weighted Image Prototypes (SWIP). SWIP builds class-wise visual anchors from temporally stable target samples to provide more reliable adaptation references. We further add a lightweight text-side refinement to reduce confusion-induced instability, and combine the two streams with an adaptive fusion rule. Across six standard benchmarks and three adaptation settings, SAST consistently outperforms strong baselines. The results suggest that explicitly modeling temporal stability is an effective route to more robust CLIP adaptation under self-training.

NeurIPS 2026

Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis

Dongyue Li, Alice Duan, Ziniu Zhang, Hongyang Zhang

We study the accumulation of test errors in language models performing multi-step reasoning. Although longer reasoning improves model capabilities by scaling test-time computation, test error compounds in autoregressive generation and can grow substantially across steps. The key factors determining the stability of such reasoning remain unclear. To address this question, we analyze the test error of multi-step reasoning under supervised fine-tuning. We first present a test error bound governed by the product of *input Jacobian spectral norms* across generation steps. This product, summarized as an error amplification factor, scales exponentially with steps and controls the reasoning stability. Then, we explicitly analyze this factor in transformers trained to predict linear and quadratic function weights. We prove that the transformer converges to a solution where this amplification factor decays, yielding near-zero test loss even over longer steps. Based on the analysis, we propose a training method to suppress the error amplification factor by combining (i) chain-of-thought length compression that reduces the reasoning steps, and (ii) quantization-aware training that provably regularizes the input Jacobian norms. We validate our method by fine-tuning language models on reasoning tasks that require executing graph algorithms and tracking variable states through logical operations. Across seven tasks, our method improves over baselines by 3.5\% on average, and by 8.2\% in length generalization evaluations. We further validate that it reduces the error amplification factor in fine-tuned models.

NeurIPS 2026

Stability and Diversity of Networked Self-Consuming Generative Ecosystems

Xiukun Wei, Yang Zhang, Xueru Zhang

The widespread deployment of generative AI has made it increasingly difficult to distinguish synthetic content from real data. Consequently, synthetic data is inevitably incorporated into the training pipelines of future model generations, forming a *self-consuming training loop*. Prior work has studied the effects of such recursive self-consuming training, but analyses have largely been limited to *isolated* models, where a model consumes only its own synthetic data, or to simplified interactions between two models. This paper takes a first step toward understanding *networked* self-consuming generative models, in which multiple models consume synthetic data generated by one another through complex interaction pathways. We introduce a theoretical framework representing models as nodes in a directed, weighted graph, with edge weights governing the flow of synthetic data among models. Using this framework, we analyze the long-term behavior of networked models under retraining dynamics, establishing conditions for convergence and characterizing the resulting fixed points. We further investigate how the system's long-term stability and diversity are shaped by each model’s access to real data, cross-model data consumption, and the structure of the interaction graph.

NeurIPS 2026

Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models

Victor De Lima, Jiqun Liu, Grace H Yang

AI systems increasingly shape how individuals access and evaluate information, intensifying concerns about misinformation. Computational simulation offers a controlled complement to direct empirical study, with fine-tuned LLMs enabling powerful agent-based simulations. However, fine-tuning often induces broad behavioral shifts including bias drift, degenerate heuristics, and loss of task competence, which undermine experimental validity. The central challenge is inducing localized decision shifts without global behavioral collapse. We study this through a stability analysis of supervised fine-tuning, attenuating loss on selected training slices to shift false-claim acceptance while preserving overall task competence. We introduce FrameRef, a large-scale dataset of semantically equivalent claims with controlled surface framings across five dimensions (Authoritative, Consensus, Emotional, Sensationalist, Prestige), with human validation confirming systematic framing effects on claim acceptance. We identify stability regimes in which targeted error shifts can be induced without degrading aggregate accuracy or calibration. A sequential exposure task over FrameRef shows that small framing-conditioned shifts compound into substantially different cumulative outcomes under feedback, but largely disappear when feedback is removed, confirming that interventions modify specific decision tendencies rather than global performance. We release code, LoRA adapters, and data at https://github.com/anonymousauthor2352/frameref.

NeurIPS 2026

StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching

Thomas Ressler-Antal, Frank Fundel, Malek Ben Alaya, Stefan Andreas Baumann, Bjorn Ommer

Latent action models (LAMs) aim to learn compact representations of state transitions directly from visual observations, but they suffer from a fundamental ambiguity: the latent code can encode target-state information rather than true dynamics. Existing approaches address this issue through restrictive bottlenecks, which reduce leakage at the cost of limiting expressivity. We propose StaDy, a regularization framework that instead enforces conditional informativeness: the latent code should aid prediction only when paired with the source state, while remaining uninformative about the target on its own. Concretely, we introduce a likelihood-matching objective that aligns the decoder’s predictions conditioned solely on the latent variable with its unconditional predictions. This discourages target memorization without constraining latent capacity. Experiments in video modeling show that, unlike bottleneck-based methods, StaDy scales effectively with increased latent dimensionality, reducing static content leakage while improving the representation of more complex dynamics.

NeurIPS 2026

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

Jian Zhu, Yuzheng Zhang, Zeyao Ma, Bohan Zhang, Armin Schoepf, Daniel Woloch, Peter Wang, Guangyu Robert Yang, Samuel Jacob, Siddharth Nagisetty, Abhiram Chundru, Jean Lin, Spencer Mateega, Jing Zhang

Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate isolated operations such as single-formula generation or local cell edits, and therefore fail to capture end-to-end workflows in realistic business settings. We introduce SpreadsheetBench 2, a workflow-level benchmark for spreadsheet agents that covers three task categories: generation, debugging, and visualization. The benchmark is constructed from authentic business data, including financial reports and corporate filings, and is annotated and validated by domain experts. The benchmark contains 321 tasks; each instance averages 11.8 worksheets and requires 593.5 cell modifications, reflecting large multi-sheet workbooks with cross-sheet dependencies. We evaluate eight frontier large language models under a unified multi-turn agent scaffold, and additionally include several LLM-based spreadsheet products as complementary baselines. Results show that current systems remain far from reliable on real-world workflows: the best model achieves 34.89% overall task accuracy, and debugging accuracy is as low as 12.00%. Trajectory analysis and a failure taxonomy further indicate that insufficient spreadsheet inspection and incorrect target-cell selection are the dominant bottlenecks. Together, these findings position SpreadsheetBench 2 as a challenging testbed for advancing reliable spreadsheet automation.

NeurIPS 2026

Sport Is The Next Grand Challenge For Artificial Intelligence: Toward A Science Of Human Physical Skill

Katia Bourahmoune, Karlos Ishac

We argue that sport represents the next grand challenge for Artificial Intelligence, a domain rich enough to expose the limits of current approaches and structured enough to drive rigorous scientific progress in understanding and modelling human physical skill. Despite rapid advances in language, vision, and robotic manipulation, the physical intelligence required to learn and adapt complex motor skills remains poorly understood and largely unaddressed. We identify two intertwined gaps: the absence of models for human physical skill, and the absence of the scientific agenda needed to build them. We propose concrete directions for how the community can begin to close both.

NeurIPS 2026

Sponsored Questions and How to Auction Them

Kshipra Bhawalkar, Alexandros Psomas, Di Wang

Online platforms connect users with relevant products and services using ads. A key challenge is that a user's search query often leaves their true intent ambiguous. Typically, platforms passively predict relevance based on available signals and in some cases offer query refinements. The shift from traditional search to conversational AI provides a new approach. When a user's query is ambiguous, a Large Language Model (LLM) can proactively offer several clarifying follow-up prompts. In this paper we consider the following: what if some of these follow-up prompts can be ``sponsored,'' i.e., selected for their advertising potential. How should these ``suggestion slots'' be allocated? And, how does this new mechanism interact with the traditional ad auction that might follow? This paper introduces a formal model for designing and analyzing these interactive platforms. We use this model to investigate a critical engineering choice: whether it is better to jointly optimize the user interaction and the final ad auction, or to decouple them into separate mechanisms for the suggestion slots and another for the subsequent ad slot. We show that the VCG mechanism can be adopted to jointly optimize the sponsored suggestion and the ads that follow; while this mechanism is more complex, it achieves outcomes that are efficient and truthful. On the other hand, we prove that the simple-to-implement modular approach suffers from strategic inefficiency: its Price of Anarchy is unbounded, for various natural choices for the two mechanisms. While we show that this inefficiency can be mitigated through revenue redistribution, we argue that the resulting mechanism sacrifices the practical simplicity that motivated the modular design in the first place.

NeurIPS 2026

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving

Yipin Guo, Siddharth Joshi

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound prefill phase and the memory-bound decode phase. Under this design, prefill workers generate a KV cache that must be transferred to decode workers before token generation can begin. With these workers residing on different physical systems, this transfer becomes a significant bottleneck to serving LLMs at scale. This bottleneck gets exacerbated for long-input and agentic workloads. Existing lossless codecs are not suited to this setting as they primarily target offline weight compression, run on the CPU, or use variable-length coding whose decompression is fast but compression is too slow to keep up with KV production during prefill. We introduce SplitZip, a GPU-friendly lossless compressor for KV-cache transfer that preserves KV tensors bitwise and integrates into existing serving frameworks without changes to model execution. SplitZip exploits redundancy in floating-point exponents of KV activations, encoding the most frequent exponent values with fixed-length codes and routing rare exponents through a sparse escape stream of (position, value). An offline calibrated top-16 exponent codebook eliminates online-histogramming, while the regular dense path and sparse escape correction make both encoding and decoding efficient on GPUs. On real BF16 activation tensors, SplitZip achieves 613.3 GB/s compression throughput and 2181.8 GB/s decompression throughput, substantially outperforming prior lossless compressors on the latency-critical codec path. End-to-end transfer experiments show up to 1.32× speedup for BF16 KV-cache transfer, 1.30× speedup for TTFT, and 1.23× increase on Request Throughput. The same approach extends to FP8 KV caches, providing up to 1.14× compression over native E5M2.

NeurIPS 2026

Split-and-scale Latent 3D Representations

Dorian Chan, Muhammed Kocabas, Xiaoming Zhao, Oncel Tuzel, Jen-Hao Chang

Latent 3D representations have significantly expanded the capabilities of modern shape modeling, enabling compact encoding of 3D scenes and supporting powerful 3D generative models. Despite this progress, current representations struggle to capture the fine details of complex objects, fundamentally limited by the capacity of their latents. However, scaling latent capacity at training time is computationally expensive and often infeasible under memory limits, and naively increasing the number of latents at inference fails to make effective use of the added capacity. In this paper, we address both challenges with split-and-scale, a method that effectively expands latent capacity at inference while keeping training cost tractable. Our key observation is that by representing 3D scenes as continuous functions of 3D coordinates, a single pretrained tokenizer can be applied at inference to arbitrarily small sub-regions of a scene, allocating the same latent capacity to a smaller spatial extent and thus capturing far higher detail. We validate this insight by conducting extensive ablations to study the trade-offs between compute, memory, latent capacity, and reconstruction quality, demonstrating our inference-time scaling method achieves quality competitive with much larger models that exceed single-GPU memory limits. We further demonstrate that split-and-scale supports high-quality generative modeling, training an autoregressive 3D generator that performs competitively with state-of-the-art baselines.

NeurIPS 2026

Split-RL: Local Conflict Resolution in Reinforcement Learning

Benjamin Fuhrer, Chen Tessler, Gal Dalal

We introduce Split-RL, a reinforcement learning (RL) algorithm based on decision trees. It uses guidance labels to explicitly partition the state-space and isolate localized conflicting signals. RL policies are often trained by mixing contradictory feedback that is localized in space and time. For example, a robot may prioritize speed in open areas versus precision in tight gaps. These regions are often easily detectable from sensor data or a human operator. Standard neural networks (NNs) lack the structural mechanism to isolate these signals. While Gradient Boosting Trees (GBT) provides the inductive bias to explicitly partition the state-space, standard tree-fitting procedures fit only aggregated gradients, merging contradictory updates before they reach the leaves. Split-RL leverages this bias to integrate guidance labels into tree construction, routing these updates into disjoint regions of the state-space to prevent signal interference during training. Such labels can arise from simple heuristics, sensor-derived events, or existing rule-based systems, allowing Split-RL to incorporate rule-derived structure while retaining a learned policy. We theoretically show how early gradient aggregation loses objective-specific information and characterize when the Split-RL score isolates conflicting updates. Finally, we evaluate Split-RL on constrained tasks and offline imitation learning from mixed-quality datasets. Across constrained domains with spatial, rare-event, and temporal conflicts, Split-RL consistently outperforms existing methods by achieving low-cost, feasible solutions while maintaining competitive rewards. In offline settings, Split-RL localizes the tradeoff between imitation and policy improvement, outperforming other methods and achieving near-expert performance across varying dataset sizes.

NeurIPS 2026

Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation

Ziyad Sheebaelhamd, Luca Viano, Volkan Cevher, Claire Vernade

This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts in a Multi-Objective Markov Decision Process (MOMDP). Standard imitation approaches are ill-equipped for this regime, as naively aggregating conflicting expert trajectories can result in dominated policies. To address this, we introduce Multi-Output Augmented Behavioral Cloning (MA-BC), an algorithm that systematically partitions divergent expert data while pooling state-action pairs where no behavior conflict is observed. Theoretically, we prove that MA-BC converges to Pareto-optimal policies at a faster statistical rate than any learner that considers each expert dataset independently. Furthermore, we establish a novel lower bound for multi-objective imitation learning, demonstrating that MA-BC is minimax optimal. Finally, we empirically validate our algorithm across diverse discrete environments and, guided by our theoretical insights, extend and evaluate MA-BC on a continuous Linear Quadratic Regulator (LQR) control task.

NeurIPS 2026

Split Then Select: Moment-Preserving Density Control for Generalized Primitive Splatting

Yangkai Lin, Jiehong Lin, Kui Jia

Primitive splatting has become a powerful representation for efficient differentiable rendering, but existing density-control strategies remain largely heuristic and often suffer from uncontrolled primitive growth. In this work, we present \textbf{Moment-Preserving Density Control (MPDC)}, a general theoretical framework for densification in primitive splatting. Unlike conventional density-control strategies that \emph{select first and split later}, MPDC follows a \emph{split-then-select} paradigm. Our key insight is that a principled split should first preserve the current rendering, rather than immediately perturb the image. By matching local moments, MPDC decomposes a primitive into multiple offspring while keeping the rendered output, and hence the loss, unchanged up to higher-order error. Although such a split does not directly reduce the loss, it changes the parameter space: a saddle point in the original parameterization may no longer remain a saddle point after splitting. This provides a distinct saddle-escaping mechanism from prior approaches that move primitives along negative-curvature directions. Building on this view, we derive closed-form splitting rules for different primitive parameterizations and then select only primitives whose moment-preserving splits reduce an upper bound of the loss through a splitting-matrix criterion. Experiments on three diverse primitive splatting methods show that MPDC substantially reduces primitive counts without sacrificing rendering quality, while improving memory efficiency and rendering speed. Code will be released upon publication.

NeurIPS 2026

SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants

Santanu Rathod, Pietro Lio, Xiao Zhang

Flow matching is an emerging, scalable generative framework for characterizing continuous normalizing flows with wide-range applications. However, state-of-the-art methods are not well-suited for modeling dynamical systems, as they construct conditional paths that are restricted to linear interpolants, a suboptimal supervision signal, which may not capture the system's underlying state evolution. Moreover, constructing unified paths to satisfy multi-marginal constraints across observations is challenging, since naïve higher-order polynomials tend to be unstable and oscillatory. To address these limitations, we introduce SplineFlow, a theoretically grounded flow matching algorithm that jointly models conditional paths across observations via B-spline interpolation. Specifically, SplineFlow exploits the smoothness and stability of B-spline bases to learn the complex underlying dynamics in a structured manner while ensuring the multi-marginal requirements are met. Comprehensive experiments across deterministic and stochastic dynamical systems under various configurations, as well as cellular trajectory inference tasks, demonstrate that SplineFlow outperforms existing baselines, especially when the underlying dynamics are of higher degree or in irregular sampling regimes.

NeurIPS 2026

Splatting the Invisible: Geometry and Appearance Scene Completion from Sparse Views

Wesley Khademi, Fuxin Li

Novel view synthesis methods such as 3D Gaussian Splatting degrade under sparse-view settings, suffering from an inability to extrapolate beyond observed regions. To enable high fidelity reconstruction and rendering from sparse views, inpainting of sparsely observed areas and completion of occluded regions is required. Unlike existing approaches that perform these tasks using 2D inpainting diffusion models or geometric-only 3D completion models, we propose a fully 3D scene completion framework, called InvisiSplat, that performs geometry and appearance completion directly in 3D. Our method consists of a Gaussian Splat VAE which learns a sparse point cloud latent space that predicts Gaussian Splat parameters from the latents, as well as a two-step flow model that learns to generate samples conditioned on the point cloud latents, different from other approaches that use tokens without 3D coordinates. Our flow model utilizes alternating local 3D attention and global attention, which balances the needs for precise local geometry and large-scale spatial context. Across several datasets, we demonstrate that our method produces 33% - 82% higher fidelity 3D geometry over prior work while attaining competitive performance on appearance metrics when compared to existing approaches.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.