NeurIPS 2026 论文列表

Distributional Reinforcement Learning methods aim to learn the entire distribution of returns, yet current algorithmic approaches are limited to a narrow class of distributions. We propose $\varphi$TD, a method to overcome this limitation through computing the loss in the frequency domain. We demonstrate that this further unifies quantile and categorical approaches to distributional RL, as well as enabling the learning of distributions that were previously impossible to capture, such as mixtures of continuous distributions. We empirically study $\varphi$TD across synthetic benchmarks and large-scale deep RL environments, and demonstrate that the flexibility obtained by wider parametric families often leads to improved performance.

While text-to-image (T2I) diffusion models exhibit strong semantic disentanglement at the object level, they struggle to localize fine-grained object parts. Although the latent visual features in these models are sufficiently fine-grained, the text–image interaction (cross-attention) fails to effectively exploit this information. This results in coarse and ambiguous localization, particularly for spatially distinct components such as `left` and `right` limbs. To address this limitation, we introduce **PartConcepts, a mechanism that encodes textual part descriptions into compact, learnable representations**. These PartConcept tokens are trained to selectively attend to their corresponding part regions in the image. To evaluate the part-level understanding of PartConcept tokens, we first probe its effectiveness for *part segmentation*. We then evaluate whether the improved localization enables *fine-grained instruction following* in T2I generation. On the standard **Open-Vocabulary Part Segmentation (OVPS) benchmark, our method outperforms dedicated segmentation baselines**, establishing a new state-of-the-art. We further evaluate our method on the more complex Pascal-Part benchmark for *part instance segmentation*, which contains fine-grained spatial annotations (e.g. `left lower arm`). Here, we outperform all baselines by a very significant margin. Finally, our qualitative and quantitative results show that this strong localization of PartConcept tokens directly enables *fine-grained instruction following* in T2I generation: the textual attributes (e.g., color) *inherently* bind well to corresponding PartConcept tokens, without explicit attribute control mechanisms. This indicates that PartConcept tokens compose seamlessly with other text tokens, highlighting their applicability for **fine-grained text-based generative control**.

Vision-Language-Action Models (VLAs) enable robots to perform manipulation tasks by leveraging Vision-Language Models (VLMs) to process visual observations and language instructions. However, the action prediction objective itself lacks fine-grained task-specific perceptual supervision, making it prone to relying on task-irrelevant visual shortcuts, leading attention away from target objects and key interaction areas, thereby limiting its operational performance and generalization ability. To address this, we propose Automatic Perception-Guided Attention Alignment for Robot Manipulation ($\text{A}^3$-VLA), a framework that derives task-specific visual guidance from the manipulation process itself. Specifically, $\text{A}^3$-VLA first generates heuristic candidate regions for target objects and the robot from interaction-induced visual changes, and refines them with a visual segmentation model offline. These regions serve as explicit perceptual guidance through two complementary objectives: an attention allocation loss that encourages sufficient focus on task-critical regions when language or robot state tokens query the visual input, and a contrastive learning loss that aligns the representations of candidate target regions with language instructions while separating them from task-irrelevant regions. Extensive experiments on simulated and real-world manipulation tasks demonstrate that $\text{A}^3$-VLA consistently improves multiple VLA backbones, with an average success rate gain of 6.5\% - 25.2\% across benchmarks.

Many machine learning tasks are invariant under the action of a group $G$ of transformations: signal classification can be invariant under translations, image classification under 2D rotations, and spherical-image classification under 3D rotations. The $G$-bispectrum is a principled complete invariant of a signal )retaining all signal's information up to the group action) with proven benefits in machine learning and as a pooling layer in deep networks. However, its deployment has been hampered by high computational cost and a patchwork of group-specific implementations. We present bispectrum, an open-source, fully unit-tested PyTorch library that implements selective $G$-bispectra for seven different group actions, as differentiable modules that can be directly incorporated into machine learning pipelines and deep learning architectures. For finite groups $G$, selectivity reduces the computational cost from $O(|G|^2)$ to $O(|G|)$. For planar rotations, we leverage the disk bispectrum. For spherical 3D rotations, we introduce an augmented selective bispectrum at band-limit $L$ which reduces the cost from $O(L^3)$ to $\Theta(L^2)$ coefficients. We profile the entire library (for

Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex sequence-function relationships, and the narrow space of biologically viable sequences. Generative methods that drift away from the data manifold can yield sequences that fail to fold, translate poorly, or are otherwise nonfunctional. We present RNAGenScape, a property-guided manifold Langevin dynamics framework for mRNA sequence generation that operates directly on a learned manifold of real data. By performing iterative local optimization constrained to this manifold, RNAGenScape preserves biological viability, accesses reliable guidance, and avoids excursions into nonfunctional regions of the ambient sequence space. The framework integrates three components: (1) an autoencoder jointly trained with a property predictor to learn a property-organized latent manifold, (2) a denoising autoencoder that projects updates back onto the manifold, and (3) a property-guided Langevin dynamics procedure that performs optimization along the manifold. Across three real-world mRNA datasets spanning two orders of magnitude in size, RNAGenScape increases median property gain by up to 148% and success rate by up to 30% while ensuring biological viability of generated sequences, and achieves competitive inference efficiency relative to existing generative approaches.

Systematicity is the capacity to generalize compositionally. Existing benchmarks primarily test behavioral systematicity, while representation-level analyses often leave open whether recovered signals are merely decodable or causally used during generation. We therefore introduce $\mathrm{Bounded\mbox{-}RS}$, an evaluation artifact and protocol for adjudicating these possibilities under bounded hypotheses: unsupported, present-only, causal-use, or underdetermined. The artifact is a controlled semantic-parsing setting with matched recombination tests, exact intervention pairs, and evidence routines for recoverability, interchange, necessity, and repair during generation. We apply $\mathrm{Bounded\mbox{-}RS}$ to the two prominent representation-level explanations of systematic generalization, binding and geometry. Within the family instantiations evaluated here, and under the same behavioral anchor and state semantics, the binding family satisfies the criteria for $\mathit{Causal\mbox{-}use}$, whereas the geometry family is adjudicated as $\mathit{Unsupported}$ under its frozen closure basis. Detector-truthfulness tests do not validate a geometry detector, so the geometry conclusion remains a claim about the tested family rather than about all possible geometric mechanisms. $\mathrm{Bounded\mbox{-}RS}$ thus provides a reusable way to make disciplined representational claims from behavioral systematicity tests.

Projection-based optimization offers a gradient-free alternative to conventional gradient-based methods, but existing frameworks suffer from high computational costs and poor scaling with depth. We introduce $\mathcal{P}$Torch, a projection-based framework that builds directly on top of PyTorch's autograd engine, eliminating the overhead of prior approaches. We further improve performance through nonlinear relaxation and memory-efficient projections. Together, these contributions make the algorithm competitive with gradient-based methods for shallow MLPs on MNIST and CIFAR-10. Finally, we prove a vanishing target theorem showing that the layer-wise learning signal decays with increased depth, serving as an analogue of the vanishing gradients problem for projection-based methods.

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic segmentation largely underexplored. In this work, we identify three key challenges for segmentation DD: (*i*) long-tailed class imbalance, (*ii*) the need for strict pixel-wise alignment between images and dense labels, and (*iii*) the high computational cost of optimizing high-resolution data with complex models. To address these challenges, we propose $\mathbf{D^{3}S^{2}}$, a **D**iffusion-guided **D**ataset **D**istillation framework for **S**emantic **S**egmentation. Our method adopts a two-stage design. In **Class-Balanced Mask Selection**, we construct a representative mask set via a greedy strategy that prioritizes underrepresented classes. In **Diffusion-Guided Image Synthesis**, we employ a pretrained layout-to-image diffusion model to generate images conditioned on the selected masks, naturally ensuring spatial alignment. To further enhance the training utility of synthesized data, we introduce guided diffusion sampling with two complementary objectives: a segmentation-consistency loss for pixel-level alignment, and a class-wise feature matching loss for aligning per-class feature statistics across layers. Extensive experiments demonstrate the superiority of $D^{3}S^{2}$. Notably, at an extremely compression rate of 1\%, our method achieves 24.99\% and 35.49\% mIoU on ADE20K and COCO-Stuff with Mask2Former (Swin-S), outperforming random selection by 9.34\% and 5.70\%, respectively.

Optimizing non-convex functions is a fundamental challenge across machine learning and combinatorial optimization. We introduce and study $\gamma$-weakly $\theta$-up-concavity, a novel first-order condition that characterizes a broad class of such functions. This condition provides a powerful unifying framework, strictly generalizing both DR-submodular and One-Sided Smooth (OSS) functions while capturing broader forms of scale-dependent curvature, including accumulating-then-diminishing returns and flat-start behavior. Our central theoretical contribution demonstrates that $\gamma$-weakly $\theta$-up-concave functions are upper-linearizable: for any feasible point, we can construct a linear surrogate whose gains provably approximate the original non-linear objective. A key technical contribution is a nonuniform upper-linearization argument yielding approximation coefficients that depend explicitly on the curvature parameters and the geometry of the feasible region. This linearizability yields immediate and unified approximation guarantees for a wide range of problems. Specifically, we obtain unified approximation guarantees for offline optimization as well as static and dynamic regret bounds in online settings via standard reductions to linear optimization. Moreover, our framework recovers the optimal approximation coefficient for DR-submodular maximization and improves existing approximation coefficients for OSS optimization, particularly over matroid constraints.

Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and often fails to ensure effective context utilization. We propose $\delta$-Mem, a lightweight memory mechanism that augments a frozen full-attention backbone with a compact online state of associative memory. $\delta$-Mem compresses past information into a fixed-size state matrix updated by delta-rule learning, and uses its readout to generate low-rank corrections to the backbone's attention computation during generation. With only an $8\times8$ online memory state, $\delta$-Mem improves the average score to $1.10\times$ that of the frozen backbone and $1.15\times$ that of the strongest non-$\delta$-Mem memory baseline. It achieves larger gains on memory-heavy benchmarks, reaching $1.31\times$ on MemoryAgentBench and $1.20\times$ on LoCoMo, while largely preserving general capabilities. These results show that effective memory can be realized through a compact online state directly coupled with attention computation, without full fine-tuning, backbone replacement, or explicit context extension.

End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: *policy density*, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role *composition*: a single task requires the agent to play multiple roles with handoffs; and *multilateral interaction*: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce $\chi$-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document *managed-care operations handbook* skill. Across 30 agent harness/models configurations, the best agent resolves only **28.0%** of tasks, no agent clears **20%** on strict pass^3, and executing all tasks in a single session slumps the performance to **3.8%**. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.

Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency but structurally deviates from the ideal on-policy objective. To address this challenge, we theoretically decompose the objective discrepancy into rollout drift and supervision drift, capturing staleness in student occupancy and teacher context, respectively. Building on this, we introduce a sample-level freshness score that quantifies the reliability of buffered sample with respect to the on-policy objective. Guided by this signal, we further propose $\boldsymbol{f}$**-OPD**, a novel framework that adaptively regulates stale-sample influence and constrains policy drift accumulated under asynchronous optimization. Across reasoning, tool-use, and coding-agent tasks of increasing interaction horizon, $f$-OPD consistently achieves task performance comparable to synchronous training while retaining the throughput advantages of asynchronous execution. Our results establish the first recipe that seeks to achieve a performance–efficiency trade-off in OPD, paving the way for long-horizon agentic post-training at scale.

Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of foreground and background. Existing depth models primarily predict single-layer depth, leading to ambiguity in depth correspondence at soft boundaries. While matting techniques can capture opacity for layered modeling, they often struggle in complex scenes with multiple targets and usually require user intervention. This paper introduces $\alpha$Depth, a layered representation that decomposes soft boundaries for high-fidelity stereo conversion. Specifically, we first resolve mixed color and depth ambiguity by estimating layered color and depth values at soft boundaries. Considering complex multi-target scenes, we design a Circular Alpha Representation (CAR) that shifts the paradigm from global target extraction to local boundary decomposition. Unlike prior matting methods restricted to a single foreground/background, CAR enables efficient scene-level inference without manual guidance. Extensive evaluations demonstrate that $\alpha$Depth achieves state-of-the-art performance in stereo conversion, eliminating background bleeding and structural distortions at soft boundaries.

Vehicle trajectory generation is critical for autonomous driving simulation. However, current generative models face two coupled limitations: (i) imbalanced trajectory distributions bias them toward frequent motions, such as straight driving or stationary states, while weakening their ability to synthesize rare but safety critical motions, such as turning. (ii) Euclidean intermediate spaces provide limited geometric inductive bias for modeling vehicle pose evolution. Together, these limitations lead to mode biased generation and physically less coherent trajectories. To address this issue, we propose SEA, an \underline{\textbf{SE}}(2)-\underline{\textbf{A}}ware vehicle trajectory generation method that realizes the conditional transport path through planar rigid body poses. At the \textbf{data distribution} level, SEA learns vehicle trajectory distributions from traffic data to capture individual motion characteristics. At the \textbf{physical-space} level, motivated by the geometry dependence of {\bf optimal transport} interpolation, SEA realizes intermediate transport states through an $SE(2)$-consistent construction, thereby preserving geometric interpretability and physical coherence during generation. Extensive experiments on large scale real world datasets show that our method outperforms state of the art approaches by generating more realistic, diverse and dynamically consistent trajectories.

Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. However, these models are typically constrained by a global coordinate frame assumption. This dependency becomes a significant bottleneck for long-context and streaming reconstruction, as it forces the network to maintain an arbitrary temporal origin and handle translation magnitudes that grow unbounded over time. Our solution, which we call $R^3$, employs relative regression. We employ a lightweight MLP to predict confidence-weighted relative constraints. These confidences serve as a unified anchor: weighting losses during training and guiding pose aggregation during inference. $R^3$ supports both full-context offline reconstruction and causal, bounded-memory streaming. Our evaluation in both offline and streaming settings validates the effectiveness of our relative mechanism.

Designing effective reward functions is a critical challenge in Reinforcement Learning (RL), which traditionally requires costly manual trial-and-error. While Large Language Model (LLM)-based methods have shown promise in reward design, undifferentiated sampling and limited use of historical feedback often lead to insufficient exploration of the reward space and optimization instability. To address these challenges, we propose $R^2E$, a Role-driven Reward Evolutionary framework for automated reward function design that structures the process through explicit role specialization. $R^2E$ employs multiple LLM roles with complementary objectives: an Explorer that promotes novelty to expand the search space, a Guardian that performs conservative refinements to improve training stability, and an Evolver that recombines high-performing rewards via crossover and mutation to integrate effective structures. A dynamic scheduling strategy coordinates these roles, progressively shifting the search from broad exploration to focused exploitation. To mitigate optimization instability and provide a medium for cross-role collaboration, $R^2E$ incorporates a Global Elite Pool that retains the best-performing rewards to guide subsequent generations, thereby enabling coordinated interaction among roles and ensuring a reliable and consistent refinement process. Extensive experiments on multiple robotic tasks demonstrate the effectiveness of our method.