论文检索

Reinforcement Learning · Deep RL

Hikmet Simsir, Ozgur S. Oguz

Behavior cloning with high-capacity generative policies achieves strong imitation performance, but performance is often constrained by limited demonstration coverage and sensitivity to distribution shift. While reinforcement learning can improve task performance, directly fine-tuning large action decoders is often unstable and sample inefficient. We propose **Lagrangian Perturbation Diffusion Steering (LP-DS)**, a lightweight adaptation method that improves a frozen generative policy while preserving its multimodal structure. LP-DS learns a compact noise-space perturbation module that shifts Gaussian noise inputs before decoding, enabling policy improvement without modifying the action decoder. To prevent off-manifold latent queries and unstable denoising dynamics, we optimize this module with a Lagrangian trust-region objective that maximizes downstream value while constraining perturbation magnitude, yielding stable and sample-efficient learning. Across RoboMimic manipulation, OpenAI Gym locomotion, and Adroit dexterous manipulation benchmarks, LP-DS improves sample efficiency, success, and return while maintaining diverse behavior, as quantified by higher action-space entropy using the Kozachenko--Leonenko k-nearest neighbor estimator, with return improvements of up to 25\% over prior baselines. Anonymous project page: https://sites.google.com/view/lp-ds/home.

Applications · Health / Medicine

Xiaoda Wang, Ching Chang, Defu Cao, Kaiqiao Han, Fang Sun, Yue Huang, Minxiao Wang, Chang Xu, Xiao Luo, Runze Yan 等

Physiological waveforms (e.g., ECG, PPG, EEG) encode clinically meaningful information in fine-grained morphology, precise timing, and cross-channel dynamics, yet most machine learning systems still treat them as generic time series and optimize end-to-end prediction. In this position paper, **we argue for verifiable physiological waveform reasoning: extracting localized, measurable signal evidence from raw signals, interpreting that evidence into physiological semantics, and supporting clinically grounded decisions.** Waveform reasoning is challenging due to acquisition heterogeneity, signal fidelity, complex semantics and cross-channel coupled dynamics. We analyze why existing model families remain insufficient: physiological foundation models learn strong perceptual representations but remain weak at verifiable reasoning, while LLM-based adaptations have limited waveform understanding. To bridge this gap, **we advocate verifiable, closed-loop systems that unify waveform semantics with language intelligence.** Concretely, we propose a dual-process architecture that System 1 aligns physiological waveforms with language, and System 2 provides agentic reasoning via a Plan--Act--Verify loop, together enabling verifiable physiological waveform reasoning. We further propose evaluations beyond accuracy, emphasizing traceability, replayability, counterfactual robustness, and calibrated abstention.

Deep Learning · Large Language Models

Samuele Marro, Phil Torr

While the Internet's core infrastructure was designed to be open and universal, today’s application layer is dominated by closed, proprietary platforms. Open and interoperable APIs require significant investment, and market leaders have little incentive to enable data exchange that could erode their user lock-in. We argue that LLM-based agents fundamentally disrupt this status quo. Agents can automatically translate between data formats and interact with interfaces designed for humans: this makes interoperability dramatically cheaper and effectively unavoidable. We name this shift *universal interoperability*: the ability for any two digital services to exchange data seamlessly using AI-mediated adapters. Universal interoperability undermines monopolistic behaviours and promotes data portability. However, it can also lead to new security risks and technical debt. Our position is that the ML community should embrace this development while building the appropriate frameworks to mitigate the downsides. By acting now, we can harness AI to restore user freedom and competitive markets without sacrificing security.

Reinforcement Learning · Everything Else

Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han, Chenyi Tong, Haoran Deng, Alexander Taylor, Renliang Sun 等

Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. In this paper, we first propose $\textbf{ARLArena}$, a fair and systematic analysis framework that encompasses a broad spectrum of ARL algorithms and decomposes policy optimization (PO) through multiple policy gradient dimensions. Through this fine-grained analysis, we distill a unified perspective on ARL and, guided by the identified governing factors, propose $\textbf{SAMPO}$, a stable agentic PO method designed to mitigate the dominant sources of instability in ARL. Empirically, SAMPO achieves consistently stable training and strong performance across diverse agentic tasks. Overall, this study provides a unifying policy gradient perspective for ARL and offers practical guidance for building stable and reproducible LLM-based agent training pipelines. Our codebase is open-sourced at https://anonymous.4open.science/r/SAMPO-02B3.

Applications · Chemistry, Physics, and Earth Sciences

Eike S. Eberhard, Luca Anthony Thiede, Abdulrahman Aldossary, Andreas Burger, Nicholas Gao, Vignesh Bhethanabotla, Alan Aspuru-Guzik, Stephan Günnemann

Machine-learned (ML) XC-functionals promise improved accuracy, but overfit to training energies and basis sets without proper regularization. We introduce Derivative Informed XC-Loss (DI-Loss), a loss that regularizes ML-XC training by supervising energy gradients on the Grassmannian of density matrices. Crucially, rather than merely matching the self-consistent fixed point, DI-Loss forces the dynamics of the SCF process to align with the target functional. Across all evaluated architectures, this improves basis set generalization and electron densities. Distilling hybrid ($\mathcal{O}(N^4)$-scaling) functionals to $\mathcal{O}(N^3)$-scaling ML-XC functionals, we observe a $>60\%$ reduction in energy MAE compared to energy and density supervision alone, while simultaneously reducing the density-dipole error by 65\%. We show that initializing from these distilled functionals can reduce hybrid SCF iterations by up to 55\%. Furthermore, DI-Loss improves TDDFT excited-state predictions by approximately 30\%.

Deep Learning · Large Language Models

Zongyue Qin, Raghavv Goel, Risheek Garrepalli, Mukul Gagrani, Mingu Lee, Yizhou Sun

Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that are subsequently verified by the target model. The effectiveness of this paradigm critically depends on the quality of the draft model. While recent advances such as the EAGLE series achieve state-of-the-art speedup, existing draft models remain limited by error accumulation: they condition only on the current prefix, causing their predictions to drift from the target model over steps. In this work, we propose ConFu (Contemplate the Future), a novel speculative decoding framework that enables draft models to anticipate the future direction of generation. ConFu introduces (i) contemplate tokens and soft prompts that allow the draft model to leverage future-oriented signals from the target model at negligible cost, (ii) a dynamic contemplate token mechanism with MoE to enable context-aware future prediction, and (iii) a training framework with anchor token sampling and future prediction replication that learns robust future prediction. Experiments demonstrate that ConFu improves token acceptance rates and generation speed over EAGLE-3 by 8-11%, across various downstream tasks with Llama-3 3B and 8B models. We believe our work is the first to bridge speculative decoding with continuous reasoning tokens, offering a new direction for accelerating LLM inference.

Deep Learning · Large Language Models

Ruijie Shi, Houbin Zhang, Yuecheng Han, Yuheng Wang, Jingru Fan, Runde Yang, Yufan Dang, Huatao Li, Dewen Liu, Yuan Cheng 等

Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and control due to opaque internal workflows. While some frameworks offer explicit architectures for collaboration, many deployed agentic systems operate as black boxes to users. We address this by introducing Agentic Workflow Reconstruction (AWR), a new task aiming to synthesize an explicit, interpretable stand-in workflow that approximates a black-box system using only input--output access. We propose AgentXRay, a search-based framework that formulates AWR as a combinatorial optimization problem over discrete agent roles and tool invocations in a chain-structured workflow space. Unlike model distillation, AgentXRay produces editable white-box workflows that match target outputs under an observable, output-based proxy metric, without accessing model parameters. To navigate the vast search space, AgentXRay employs Monte Carlo Tree Search enhanced by a scoring-based Red-Black Pruning mechanism, which dynamically integrates proxy quality with search depth. Experiments across diverse domains demonstrate that AgentXRay achieves higher proxy similarity and reduces token consumption compared to unpruned search, enabling deeper workflow exploration under fixed iteration budgets.

Applications · Computer Vision

Qin Guo, Tianyu Yang, Xuanhua He, Fei Shen, Yong Zhang, Zhuoliang Kang, Xiaoming Wei, Dan Xu

Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often suffer from face-centric behavior that neglects body-level consistency, or produce copy-paste artifacts where subjects appear rigid due to pose locking. We present Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments. Actor-18M comprises 1.6M videos with 18M corresponding human images, covering both arbitrary views and canonical three-view representations. Leveraging Actor-18M, we propose WildActor, a framework for any-view conditioned human video generation. We introduce an Asymmetric Identity-Preserving Attention mechanism coupled with a Viewpoint-Adaptive Monte Carlo Sampling strategy that iteratively re-weights reference conditions by marginal utility for balanced manifold coverage. Evaluated on the proposed Actor-Bench, WildActor consistently preserves body identity under diverse shot compositions, large viewpoint transitions, and substantial motions, surpassing existing methods in these challenging settings.

Applications · Computer Vision

Lihe Ding, Weicai Ye, Shaocong Dong, Xintao Wang, Pengfei Wan, Kun Gai, Tianfan Xue

Dynamic 3D content representation is crucial for generating moving 3D objects and scenes. Existing 4D variational autoencoders (VAEs) are mainly based on projected 2D pointmaps, which are only incomplete and view-dependent observations that do not model the native 4D positional relations between points. This often leads to projection-induced distortions and irreversible token dislocation. In this paper, we introduce a novel 4D VAE that operates directly in native 4D space, that is dynamic colored voxel space, without 2D projection. This preserves explicit spatio-temporal coordinates throughout the learned encoder and decoder, enabling both partial and complete 4D content encoding. To support a flexible temporal compression ratio, we also design a novel spatio-temporal window attention module that performs attention within local 4D windows. Additionally, we propose a differentiable voxel rendering loss based on sparse voxel rasterization to improve the geometry and color reconstruction quality. On 4D reconstruction tasks, our approach improves reconstruction fidelity over pointmap VAEs and flow-based VAEs while learning a more structurally consistent latent space. We further demonstrate the generative potential of our method by training a video-conditioned 4D diffusion model.

General Machine Learning · Hardware and Software

Zifan He, Rui Ma, Yizhou Sun, Jason Cong

Modern large language model (LLM) serving increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning. We show that these optimizations can be unified into a four-step memory processing pipeline: *Prepare Memory*, *Compute Relevancy*, *Retrieval*, and *Apply to Inference*. Through systematic profiling, we identify a 22\%-97\% memory processing overhead in LLM inference and strong heterogeneity in its computational characteristics. Motivated by this insight, we argue that \textbf{heterogeneous systems} are well-suited to accelerate memory processing and thus end-to-end inference. We demonstrate this approach on a GPU-FPGA system by offloading sparse, irregular, and memory-bounded operations to FPGAs while retaining compute-intensive operations on GPUs. Evaluated on an AMD MI210 GPU and an Alveo U55C FPGA, our system achieves $1.04\sim2.2\times$ speedup and $1.11\sim4.7\times$ energy reduction across multiple LLM inference optimizations than the GPU baseline (similar results hold on NVIDIA A100). These results establish heterogeneous systems as a practical direction for efficient LLM memory processing and inform future heterogeneous hardware design.

Applications · Computer Vision

Runsong Zhu, Jiaxin GUO, Xiaoyang Guo, Zhengzhe Liu, Ka-Hei Hui, Wei Yin, Kai Chen, Wei Chen, Weiqiang Ren, Yunhui Liu 等

This paper introduces EPS3D, a new end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation. Unlike existing methods relying on additional preprocessing, we design an end-to-end architecture, with a distillation-based training strategy on diverse 3D scenes to predict 3D-aware semantic and instance features from multi-view images, improving 3D consistency and avoiding error accumulation. We further propose a mutual enhancement module to enforce inherent semantic-instance consistency. By aligning semantics within instances (Ins2Sem) and refining instance features with semantic guidance (Sem2Ins), we achieve more coherent 3D scene understanding. Ultimately, EPS3D outperforms SOTA baselines on two benchmarks (e.g., +13\% mIoU for semantics on Replica) with high efficiency (e.g., 1s per scene), supporting tasks like robotic manipulation and 3D scene editing.

Theory · Everything Else

Takuya Koriyama, Pratik Patil, Jin-Hong Du, Kai Tan, Pierre C Bellec

We characterize the squared prediction risk of ensemble estimators obtained through subagging (subsample bootstrap aggregating) regularized M-estimators and construct a consistent estimator for the risk. Specifically, we consider a heterogeneous collection of M?1 regularized M-estimators, each trained with (possibly different) subsample sizes, convex differentiable losses, and convex regularizers. We operate under the proportional asymptotics regime, where the sample size n, feature size p, and subsample sizes km for m?[M] all diverge with fixed limiting ratios n/p and km/n. Key to our analysis is a new result on the joint asymptotic behavior of correlations between the estimator and residual errors on overlapping subsamples, governed through a (provably) contractive nonlinear system of equations. Of independent interest, we also establish convergence of trace functionals related to degrees of freedom in the non-ensemble setting (with M=1) along the way, extending previously known cases for squared loss with ridge and lasso regularizers. When specialized to homogeneous ensembles trained with a common loss, regularizer, and subsample size, the risk characterization sheds some light on the implicit regularization effect due to the ensemble and subsample sizes (M,k). For any ensemble size M, optimally tuning subsample size yields sample-wise monotonic risk. For the full-ensemble estimator (when M??), the optimal subsample size k? tends to be in the overparameterized regime (k??min{n,p}), when explicit regularization is vanishing. Finally, joint optimization of subsample size, ensemble size, and regularization can significantly outperform regularizer optimization alone on the full data (without any subagging).

Applications · Robotics

Zhaoyang Liu, Mokai Pan, Zhongyi Wang, Kaizhen Zhu, Haotao Lu, Haipeng Zhang, Jingya Wang, Ye Shi

Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions. However, existing methods typically treat observations only as high-level conditions to the denoising network, rather than integrating them into the stochastic dynamics of the diffusion process itself. As a result, the sampling is forced to begin from random noise, weakening the coupling between perception and control and often yielding suboptimal performance. We propose BridgePolicy, a generative visuomotor policy that directly integrates observations into the stochastic dynamics via a diffusion-bridge formulation. By constructing an observation-informed trajectory, BridgePolicy enables sampling to start from a rich and informative prior rather than random noise, substantially improving precision and reliability in control. A key difficulty is that diffusion bridge normally connects distributions of matched dimensionality, while robotic observations are heterogeneous and not naturally aligned with actions. To overcome this, we introduce a multi-modal fusion module and a semantic aligner to unify the visual and state inputs and align the observations with action representations, making diffusion bridge applicable to heterogeneous robot data. Extensive experiments across 52 simulation tasks on three benchmarks and 5 real-world tasks demonstrate that BridgePolicy consistently outperforms state-of-the-art generative policies.

Deep Learning · Algorithms

Wan Song, Zhou Wei, Rui Wang, Jun Yu, Toru Kurihara, Xu Jiajia, shu zhan

Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation. While Large Kernel Acceleration (LKA) helps on small feature maps, it becomes \textbf{counterproductive on large feature maps}, even slower than non-accelerated implementations. We propose Windowed Batch Matrix Multiplication (WBMM), which \emph{partitions} input into contiguous windows and \emph{indexes} a compact relative position bias table to construct weight matrices, enabling regular memory access via batched matrix multiplication; this yields a unique property where \textbf{WBMM's throughput improves with larger windows}, opposite to depthwise convolutions that degrade with larger kernels. Operator-level benchmarks show WBMM with $14 \times 14$ windows \textbf{outperforms $5 \times 5$ depthwise convolution baselines in speed} while providing $7.8\times$ larger receptive field, and combined with inter-block cross-window communication and hierarchical window reparameterization, achieves comparable or higher accuracy on ImageNet-1K, COCO, and ADE20K with 1.31--1.88$\times$ training speedup. WBMM also demonstrates consistent advantages across diverse hardware platforms including GPU, CPU, and edge devices, without requiring specialized acceleration kernels. Code and models will be publicly available.

General Machine Learning · Representation Learning

SeongMin Jin, Doo Seok Jeong

Learning latent representations that capture both semantic and spatial information is central to efficient spatio-semantic reasoning. However, many existing approaches rely on implicit latent structures combined with dense feature maps or task-specific heads, limiting computational efficiency and flexibility. We propose WorldComp2D, a novel lightweight representation learning framework that explicitly structures latent space geometry according to object identity and spatial proximity using multiscale \textit{local} receptive fields centered on a given fixation point. This framework consists of (i) a proximity-dependent encoder that maps a given observation into a spatio-semantic latent space and (ii) a localizer that infers the coordinates of objects in the input from the resulting spatio-semantic representation. Using facial landmark localization as a proof-of-concept, we show that WorldComp2D preserves fine-grained spatio-semantic representation of facial landmarks while achieving competitive accuracy at substantially low computational cost. Compared to SoTA lightweight models, WorldComp2D reduces the numbers of parameters and FLOPs by up to $4.0\times$ and $2.2\times$, respectively, while maintaining real-time performance on CPU. These results demonstrate that explicitly structured latent spaces provide an efficient and general foundation for spatio-semantic reasoning. This framework is open-sourced at https://anonymous.4open.science/r/WorldComp2D-10F6/.

Applications · Computer Vision

Josephine Elisabeth Oettinger, Zakhar Shumaylov, Johannes Bostelmann, Jan Lellmann, Carola-Bibiane Schönlieb

Incorporating group symmetries via equivariance into neural networks has emerged as a robust approach for overcoming the efficiency and data demands of modern deep learning. While most existing approaches, such as group convolutions and averaging-based methods, focus on compact, finite, or low-dimensional groups with linear actions, this work explores how equivariance can be extended to infinite-dimensional groups. We propose a strategy designed to induce diffeomorphism equivariance in pre-trained neural networks via energy-based canonicalisation. Formulating equivariance as an optimisation problem allows us to access the rich toolbox of already established differentiable image registration methods. Empirical results on segmentation and classification tasks confirm that our approach achieves approximate equivariance and generalises to unseen transformations without relying on extensive data augmentation or retraining.

Applications · Computer Vision

Wentao Zhang, Jinhu Qi, Weiqiang Jin, Yifei Zhang, Chan-Tong Lam, Irwin King

Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields inference-time physical plausibility checks. We propose Scrambled Edges, a controlled counterfactual that injects salient edge-like cues while violating surface continuity, illumination coherence, and occlusion ordering. With energy-matched and structure-matched controls, we isolate the effect of unsupported edge evidence from high-frequency energy and edge sparsity. Across CNN/ViT/SSL depth predictors on NYU Depth v2 and KITTI, Scrambled Edges induce up to 3.2× larger deviation from clean predictions than energy-matched noise. The resulting Geometric Collapse propagates globally: even with oracle knowledge of the corrupted region, output-level repair recovers only 47%, with substantial error outside the mask. These findings provide controlled behavioral evidence that current dense predictors lack reliable mechanisms to quarantine physically unsupported edge cues, motivating explicit plausibility scoring and selective cue integration.

Deep Learning · Graph Neural Networks

MD SAZZAD Hossen, Avimanyu Sahoo

Graphs with heterophily, where adjacent nodes carry different labels, are prevalent in real-world applications, from social networks to molecular interactions. However, existing spectral Graph Neural Network (GNN) approaches tailored for heterophilous graph classification suffer from hub-dominated (node with large degree) aggregation and oversmoothing, as their suboptimal polynomial filters introduce approximation errors and blend distant signals. To address the degree-biased aggregation and suboptimal polynomial filtering, we introduce a Hierarchical Multi‐view HAAR (HMH), a novel spectral graph‐learning framework that scales in near‑linear time . HMH first learns feature- and structure-aware \emph{signed} affinities via a heterophily-aware encoder, then constructs a soft graph hierarchy guided by these embeddings. At each hierarchical level, HMH constructs a sparse, orthonormal, and locality-aware Haar basis to apply learnable spectral filters in the frequency domain. Finally, skip-connection unpooling layers combine outputs from all hierarchical levels back into the original graph, effectively preventing hub domination and long-range signal bottleneck (over-squashing). Experimentation shows that HMH outperforms state‑of‑the‑art spectral baselines, achieving up to a 3 % improvement on node classification and 7% on graph classification datasets, all while maintaining linear scalability.

Applications · Computer Vision

Yeon-Ji Song, Kiyoung Kwon, Junoh Lee, Jin-Hwa Kim, Byoung-Tak Zhang

Reconstructing dynamic 3D scenes from blurry monocular videos is challenging because motion-induced blur entangles object motion and geometry, hindering geometric consistency. We present Kinematics-GS, a kinematics-aware framework that models blur as motion-aligned deformation and introduces a kinematic prior to reparameterize Gaussian shapes along motion trajectories, thereby mitigating degenerate shape collapse without auxiliary motion supervision. To stabilize optimization, we decompose scenes into dynamic and static components using temporal deformation variance and employ a coarse-to-fine deformation strategy to capture both global motion and fine-grained details. We also introduce a challenging real-world dataset of deformable and elastic objects exhibiting non-rigid motion with spatially non-uniform motion blur that obscures geometric cues. Extensive experiments on real-world benchmarks with realistic motion blur demonstrate that Kinematics-GS outperforms prior methods by a clear margin in monocular dynamic scene reconstruction, highlighting its effectiveness in handling complex and non-rigid motion scenarios.

Applications · Robotics

Quanxin Shou, Fangqi Zhu, Shuang Chen, Puxin Yan, Zhengyang Yan, Yikun Miao, Xiaoyi Pang, Zicong Hong, Ruikai Shi, Hao HUANG 等

Vision–Language–Action (VLA) models have shown strong performance in robotic manipulation, but often struggle in long-horizon or out-of-distribution scenarios due to the lack of explicit mechanisms for multimodal reasoning and anticipating how the world will evolve under action. Recent works introduce textual chain-of-thought or visual subgoal prediction within VLA models to reason, but still fail to offer a unified human-like reasoning framework for joint textual reasoning, visual foresight, and action prediction. To this end, we propose HALO, a unified VLA model that enables embodied multimodal chain-of-thought (EM-CoT) reasoning through a sequential process of textual task reasoning, visual subgoal prediction for fine-grained guidance, and EM-CoT-augmented action prediction. We instantiate HALO with a Mixture-of-Transformers (MoT) architecture that decouples semantic reasoning, visual foresight, and action prediction into specialized experts while allowing seamless cross-expert collaboration. To enable HALO learning at scale, we introduce an automated pipeline to synthesize EM-CoT training data along with a carefully crafted training recipe. Extensive experiments demonstrate that: (1) HALO achieves superior performance in both simulated and real-world environments, surpassing baseline policy $\pi_0$ by 34.1\% on RoboTwin benchmark; (2) all proposed components of the training recipe and EM-CoT design help improve task success rate; and (3) HALO exhibits strong generalization capabilities under aggressive unseen environmental randomization with our proposed EM-CoT reasoning.