Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a knowledge deficit, relying on supervised fine-tuning (SFT) to ingest labeled data from external vision sources or synthetic engines. In contrast, we argue that for many tasks, spatial capabilities are already present in pre-trained LRMs but require alignment through principles of internal logical coherence. In this work, we propose a self-supervised reinforcement learning (RL) framework that targets the internal Chain-of-Thought (CoT) process without requiring ground-truth annotations. By formalizing the notion of consistency verifiers—reward functions that check for geometric and semantic consistency under transformations like flipping or swapping the order of objects in the question—and optimizing them via our new OT-GRPO strategy, a minimal-consistency matching variant of group relative policy optimization, we demonstrate that models can self-correct their spatial logic. Our results show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and domains.
论文检索
输入标题、作者或关键词，从 8,216 篇学术成果中精准定位
General Machine Learning · Representation Learning
Video anomaly detection (VAD) is critical for surveillance systems, but current methods prioritize accuracy while ignoring the ethical risks of encoding sensitive biometric information. This neglect poses significant privacy concerns for real-world deployment. To bridge this gap, we introduce the Guided Orthogonal Projection Layer (G-OPL), a lightweight module designed to geometrically decouple and suppress sensitive attributes from latent features to produce representations focused on anomaly-relevant cues. We specifically target facial information as the primary sensitive attribute. Unlike gait or body pose, faces act as unique biometric identifiers that are tightly regulated and pose immediate risks of misuse, yet are rarely necessary for identifying abnormal behaviors. To achieve this, G-OPL utilizes a stable, QR-decomposition-based orthogonal projection mechanism guided by weak supervision (e.g., face presence) to actively filter privacy-sensitive subspaces while preserving task-relevant anomalies. we further propose a novel privacy-aware evaluation framework to rigorously quantify the trade-off between model utility and ethical alignment. Our analysis uncovers how projection layers filter sensitive information, why this improves transparency, and under what conditions ethical design also enhances robustness. Extensive experiments demonstrate that our approach effectively minimizes privacy risks without compromising anomaly detection performance, offering a principled path toward trustworthy video analysis.
Deep Learning · Large Language Models
Task-vector–based model merging enables low-cost, training-free multi-task learning for large language models, but suffers from severe performance degradation due to task conflict. Prior mitigation strategies largely rely on validation data for costly hyperparameter tuning, limiting both interpretability and practicality. We therefore propose OPIC, an evolutionary optimization–based model merging framework. Our preliminary experiments reveal that the degradation of In-Context Learning (ICL) capabilities is a primary driver of task conflict. Motivated by this insight, we formulate model merging as an optimization problem with ICL preservation as the objective. OPIC introduces a hierarchical refinement operators and optimizes it using self-generated data, effectively eliminating the reliance on external validation sets. Experimental results demonstrate that OPIC achieves an average performance retention of 80.73%, outperforming SOTA methods and improving by up to 11.1% over recent validation-free approaches. In addition, OPIC is compatible with existing merging pipelines, offering a new alternative solution for deploying without validation dependencies. Code is available at: https://anonymous.4open.science/r/OPIC-CFFE.
Applications · Computer Vision
We introduce VideoKR, the first large-scale training corpus specifically designed to strengthen knowledge- and reasoning-intensive video understanding. It comprises 430K video reasoning examples over 126K newly collected, CC-licensed, expert-domain videos. We develop an expert-in-the-loop, skill-oriented example generation pipeline that targets progressively deeper video reasoning capabilities while ensuring the difficulty, diversity, and reliability of both the examples and their CoT rationales. We also curate VideoKR-Eval, a new expert-annotated benchmark where questions require genuine video understanding and knowledge-intensive reasoning. Our experiments show that, under a standard SFT→GRPO pipeline, models post-trained on VideoKR already outperform prior post-training approaches on both general and knowledge-intensive video reasoning benchmarks, highlighting data design as a key driver of progress in video reasoning. We further conduct comprehensive ablations to isolate the contributions of VideoKR, providing actionable insights for future work.
Deep Learning · Attention Mechanisms
Designing sparse attention for 2-dimensional image data in diffusion models and vision-language models requires reconciling spatial locality with hardware-efficient execution, a fundamental trade-off that existing methods struggle to resolve. Prior approaches preserve 2D structure through handcrafted sparsity patterns, but often incur uncoalesced memory access, limiting practical speedups on modern GPUs. We present HilbertA, a 2D-aware and GPU-efficient sparse attention mechanism, and show that Hilbert curves provide a hardware-aligned inductive bias for sparse attention over 2D data. By reordering image tokens along Hilbert curves, HilbertA preserves local spatial neighborhoods while inducing a contiguous memory layout aligned with efficient GPU execution. To enable global information flow without uncoalesced access, HilbertA further employs a layer-wise sliding schedule, allowing long-range interactions to emerge progressively across depth. In addition, a small central shared region facilitates cross-tile communication and enhances positional awareness. Implemented in Triton, HilbertA achieves substantial acceleration while maintaining or improving model quality across both diffusion models and VLM. On Flux.1-dev, HilbertA delivers up to $4.17\times$ at $2048\times2048$, with image quality comparable to baselines. On Qwen3-VL-8B, HilbertA achieves over $2.08\times$ attention acceleration with $1.55\times$ improvements in Time-To-First-Token, while maintaining competitive model performance.
General Machine Learning · Online Learning, Active Learning and Bandits
Bayesian Optimization is critically vulnerable to extreme outliers. Existing provably robust methods typically assume a bounded cumulative corruption budget, which makes them defenseless against even a single corruption of sufficient magnitude. To address this, we introduce a new adversary whose budget is only bounded in the frequency of corruptions, not in their magnitude. We then derive RCGP-UCB, an algorithm coupling the upper confidence bound (UCB) approach with a Robust Conjugate Gaussian Process (RCGP). We present stable and adaptive versions of RCGP-UCB, and prove that they achieve sublinear regret in the presence of up to $O(T^{1/4})$ and $O(T^{1/7})$ corruptions with possibly infinite magnitude. This robustness comes at near zero cost: without outliers, RCGP-UCB's regret bounds match those of the standard GP-UCB algorithm.
Reinforcement Learning · Online
Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited budget remains an open challenge. We introduce PETS (\textbf{P}rincipled and \textbf{E}fficient \textbf{T}est-Time \textbf{S}elf-Consistency), which initiates a principled study of trajectory allocation through an optimization framework. Central to our approach is the \emph{self-consistency rate}, a new measure defined as agreement with the infinite-budget majority vote. This formulation makes sample-efficient test-time allocation theoretically grounded and amenable to rigorous analysis. We study both offline and online settings. In the offline regime, where all questions are known in advance, we connect trajectory allocation to crowdsourcing, a classic and well-developed area, by modeling reasoning traces as workers. This perspective allows us to leverage rich existing theory, yielding theoretical guarantees and an efficient majority-voting-based allocation algorithm. In the online streaming regime, where questions arrive sequentially and allocations must be made on the fly, we propose a novel method inspired by the offline framework. Our approach adapts budgets to question difficulty while preserving strong theoretical guarantees and computational efficiency. Experiments show that PETS consistently outperforms uniform allocation. On GPQA, PETS achieves perfect self-consistency in both settings while reducing the sampling budget by up to $75\\%$ (offline) and $55\\%$ (online) relative to uniform allocation.
Social Aspects · Safety
Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwise comparisons instead of point-wise scores, providing more robust supervision and potentially reducing reward hacking. Our RL recipe, AdvGame, shifts the Pareto frontier of safety and utility, yielding a Defender LM that is simultaneously more helpful and more resilient to adversarial attacks. In addition, the resulting Attacker LM converges into a strong, general-purpose red-teaming agent that can be directly deployed to probe arbitrary target models.
General Machine Learning · Causality
Estimating Heterogeneous Treatment Effects (HTE) from observational data is essential in fields such as healthcare and policy-making, where randomized experiments are often impractical. While representation learning-based methods have shown promise, recent studies suggest that tree-based approaches may offer superior performance on tabular data, particularly in the presence of uninformative features. We introduce **GRA**dient-based **C**ausal tree **E**nsembles (GRACE), a novel tree-based architecture for HTE estimation that incorporates multi-way, oblique, and soft splits, enabling end-to-end training via backpropagation. GRACE can be seamlessly integrated into existing models as a replacement for fully-connected neural network layers. Across diverse benchmarks involving binary and non-binary treatment settings, GRACE consistently surpasses neural network and tree-based baselines, often by a substantial margin. We further analyze GRACE as an extension of fully-connected neural network layers and conduct ablation studies to isolate and quantify the contribution of each architectural component to the improvement in performance. These results position GRACE as a powerful new foundation for flexible, robust, and accurate HTE estimation.
Deep Learning · Everything Else
Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and inference-time. However, current approaches face a critical trade-off: text-based WMs sacrifice visual fidelity, while the inability of visual WMs in precise text rendering led to their reliance on slow, complex pipelines dependent on numerous external models. We propose a novel paradigm: visual world modeling via renderable code generation, where a single Vision-Language Model (VLM) predicts the next GUI state as executable web code that renders to pixels, rather than generating pixels directly. This combines the strengths of both approaches: VLMs retain their linguistic priors for precise text rendering while their pre-training on structured web code enables high-fidelity visual generation. We introduce gWorld (8B, 32B), the first open-weight visual mobile GUI WMs built on this paradigm, along with a data generation framework (gWorld) that automatically synthesizes code-based training data. In extensive evaluation across 4 in- and 2 out-of-distribution benchmarks, gWorld sets a new pareto frontier in accuracy versus model size, outperforming 8 frontier open-weight models over 50.25x larger. Further analyses show that (1) scaling training data via gWorld yields meaningful gains, (2) each component of our pipeline improves data quality, and (3) stronger world modeling improves downstream mobile GUI policy performance.
Deep Learning · Self-Supervised Learning
The performance of sparse direct solvers is fundamentally governed by fill-in, i.e. new nonzero entries arising from the LU factorization of a sparse matrix, as they dictate memory footprint and subsequent computation time. For decades, a variety of graph-theoretic algorithms have aimed to minimize fill-in, a problem known to be both NP-hard and critically important. While recent deep learning methods, optimizing surrogate fill-in objectives, show empirical promise and can outperform classical algorithms on certain matrices, they offer limited interpretability into the underlying mechanism of fill-in generation. To address this, we propose a novel reordering approach, Causal Triplet Structure Learning (CTS), which is grounded in the Fill-Path Theorem and reduces arbitrary-length fill-paths to length-two candidate triplets, identifies the causal structures that trigger fill-in, and intervenes to block their formation. Empirically, we design a multigrid-style GAT with KAN activations to learn vertex embeddings and introduce a causal triplet loss that discourages such structures during training. Experiments on the SuiteSparse Matrix Collection demonstrate that our method reduces fill-in by 6$\times$, leading to 12$\times$ speedup in factorization time compared to state-of-the-art methods on Chemical Process Simulation and Computational Fluid Dynamics matrices.
General Machine Learning · Everything Else
Testing conditional independence is a fundamental yet inherently difficult challenge, as controlling Type I error is impossible in general. The recently popular "Model-X" paradigm offers a solution by relying on a perfectly known conditional distribution. In traditional "one-shot" testing regimes, slight deviations from perfect knowledge are sometimes allowable, but existing work in more realistic online settings has required exact adherence to Model-X. We propose a new approach for sequential testing of conditional independence that is far more robust to estimation errors in the conditional distribution. Our method, based on online optimization of the Kernel Conditional Independence statistic, introduces a novel normalization and "truncate-and-shift" calibration strategy to the testing-by-betting paradigm. This framework greatly improves validity with estimated conditionals while still providing high power across high-dimensional synthetic benchmarks and real-world fairness tasks.
Deep Learning · Large Language Models
Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we train Large Language Models (LLMs) modularly—combining small, domain-specific experts to match monolithic performance—and can we do so robustly for *any* data mixture, eliminating heuristic tuning? We present a theoretical framework for *modular* generative modeling where a set of pre-trained experts are combined via a gating mechanism. We define the space of normalized gating functions $\mathcal{G}_{1}$ and formulate the problem as a minimax game to find a single robust gate that minimizes divergence to the worst-case data mixture. We prove the existence of such a robust gate using Kakutani's fixed-point theorem and show that modularity acts as a strong regularizer, with generalization bounds scaling with the lightweight gate's complexity. Furthermore, we prove that this modular approach can theoretically outperform models retrained on aggregate data, with the gap characterized by the Jensen-Shannon Divergence. Finally, we introduce a scalable Stochastic Primal-Dual algorithm and a *Structural Distillation* method for efficient inference. Empirical results on synthetic and real-world datasets confirm that our modular architecture effectively mitigates gradient conflict and can outperform monolithic baselines.
Deep Learning · Self-Supervised Learning
Estimating the quality of register transfer level (RTL) designs is crucial in the electronic design automation (EDA) workflow, as it enables instant feedback on key performance metrics like area and delay without the need for time-consuming logic synthesis. While recent approaches have leveraged large language models (LLMs) to derive embeddings from RTL code and achieved promising results, they overlook the structural semantics essential for accurate quality estimation. In contrast, the control data flow graph (CDFG) view exposes the design's structural characteristics more explicitly, offering richer cues for representation learning. In this work, we introduce StructRTL, a novel structure-aware graph self-supervised learning framework for improved RTL design quality estimation. By learning structure-informed representations from CDFGs, StructRTL significantly outperforms prior art on various quality estimation tasks. To further boost performance, we incorporate a knowledge distillation strategy that transfers low-level insights from post-mapping netlists into the CDFG-based predictor. Experimental results demonstrate that StructRTL establishes new state-of-the-art results, highlighting the effectiveness of combining structural learning with cross-stage supervision.
Transformer architectures, and their attention mechanisms in particular, form the foundation of modern large language models. While transformer models are widely believed to operate in high-dimensional hidden spaces, we show that attention outputs are confined to a surprisingly low-dimensional subspace, with an effective dimensionality of only about 60\% of the full space---a phenomenon that is consistently observed across diverse model families and datasets, and is strongly influenced by the attention output projection matrix. Critically, we find this low-rank structure as a key factor of the prevalent dead feature problem in sparse dictionary learning, where it creates a mismatch between randomly initialized features and the intrinsic geometry of the activation space. Building on this insight, we propose a subspace-constrained training method for sparse autoencoders (SAEs), initializing feature directions into the active subspace of activations. Our approach reduces dead features from 87\% to below 1\% in Attention Output SAEs with 1M features, and can further extend to other sparse dictionary learning methods. Our findings provide both new insights into the geometry of attention and practical tools for improving sparse dictionary learning in large language models. Code is available at \url{https://anonymous.4open.science/r/Language-Model-SAEs-C015}.
Reinforcement Learning · Everything Else
Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide formal performance guarantees, which are indispensable when deploying policies in safety-critical settings. We present an approach for computing high-confidence guarantees on the performance of a multi-task policy on tasks not seen during training. Concretely, we introduce a new generalisation bound that composes (i) per-task lower confidence bounds from finitely many rollouts with (ii) task-level generalisation from finitely many sampled tasks, yielding a high-confidence guarantee for new tasks drawn from the same arbitrary and unknown distribution. Across state-of-the-art multi-task RL methods, we show that the guarantees are theoretically sound and informative at realistic sample sizes.
Applications · Computer Vision
3D editing—the task of locally modifying the geometry or appearance of a 3D asset—has wide applications in immersive content creation, digital entertainment, and AR/VR. However, unlike 2D editing, it remains challenging due to the need for cross-view consistency, structural fidelity, and fine-grained controllability. Existing approaches are often slow, prone to geometric distortions, or dependent on manual and accurate 3D masks that are error-prone and impractical. To address these challenges, we advance both the data and model fronts. On the data side, we introduce 3DEditVerse, the largest paired 3D editing benchmark to date, comprising 116,309 high-quality training pairs and 1,500 curated test pairs. Built through complementary pipelines of pose-driven geometric edits and foundation model-guided appearance edits, 3DEditVerse ensures edit locality, multi-view consistency, and semantic alignment. On the model side, we propose 3DEditFormer, a 3D-structure-preserving transformer. By enhancing image-to-3D generation with dual-guidance attention and time-adaptive gating, 3DEditFormer disentangles editable regions from preserved structure, enabling precise and consistent edits without requiring auxiliary 3D masks. Extensive experiments demonstrate that our framework outperforms state-of-the-art baselines both quantitatively and qualitatively, establishing a new standard for practical and scalable 3D editing. Dataset and code will be released. Project: https://anonymousresearch37.github.io/3DEditFormer/
Optimization · Stochastic
Distributed stochastic optimization intertwines (i) stochastic gradient noise, (ii) communication compression, and (iii) adaptive/normalized updates. While each factor has been studied in isolation, their joint effect under realistic assumptions remains poorly understood. In this work, we develop a unified theoretical framework for Distributed Compressed SGD (DCSGD) and its sign variant Distributed SignSGD (DSignSGD) under the recently introduced $(L_0, L_1)$-smoothness condition. From a conceptual perspective, we show that the first- and second-order modified equations from the literature do not accurately model the discrete-time step-size/stability restrictions, especially under $(L_0,L_1)$-smoothness. From a technical perspective, we propose new first-order SDEs by carefully incorporating curvature-dependent terms into their drift: This helps capture the fine-grained relationship between learning rate restrictions, gradient noise, compression, and the geometry of the loss landscape. Importantly, we do so under general gradient noise assumptions, including heavy-tailed and affine-variance regimes, which extend beyond the classical bounded-variance setting. Our results suggest that normalizing the updates of DCSGD emerges as a natural condition for stability, with the degree of normalization precisely determined by the gradient noise structure, the landscape’s regularity, and the compression rate. In contrast, DSignSGD converges even under heavy-tailed noise with standard learning rate schedules. Together, these findings offer both new theoretical insights and perspectives, and practical guidance.
Social Aspects · Security
Denoising diffusion sampling (DDS) is an emerging approach for generating new samples that have the same distribution as some training samples. However, it is vulnerable to adversarial attacks by even a Gaussian perturbation. In this work, we propose a complete set of adversarial attack and defense methodology for DDS. In the attack side, we propose to inject a perturbation to the sampling stage, which significantly worsen the performance of sample generation. In the defense side, we propose a local variation based regularization model for the potential function minimization, which effectively tolerates the adversarial perturbations. Moreover, we develop a conjugate gradient algorithm to solve the defense model, which integrates with a recently-developed zeroth order rejection sampling method that saves computational cost. Experimental results show that the proposed attack significantly worsen the existing state-of-the-art methods, but can be defended by the proposed local variation regularization.
Deep Learning · Large Language Models
Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs. Yet it remains unclear whether these explanations are _sufficient_, i.e., if they contain enough information to explain the model’s output-generating process. We generalize classical sufficiency from feature attributions to arbitrary explanations and prove that explanation sufficiency is inherently relative to an input distribution, which must be explicitly defined for LLM explanations. We propose using the LLM itself to generate alternative inputs conditioned on an explanation, capturing its beliefs about possible inputs. We formalize _self-consistent sufficiency_ as a goal for free-text explanations and introduce an information-theoretic metric, SCSuff, that enables evaluation of free-text explanations without relying on predefined biases or shortcuts. Our experiments show that SCSuff aligns with targeted perturbation tests where applicable and demonstrate that explanation sufficiency can vary with the input distribution. We further find that SCSuff is uncorrelated with model size, accuracy, or uncertainty, suggesting that improving self-consistent sufficiency requires approaches beyond scaling or standard performance optimization.