论文检索

Deep Learning · Algorithms

Zhongnan Cai, Yingying Wang, Hui Zheng, Panwang Pan, Zixu Lin, Ge Meng, Chenxin Li, Chunming He, Jiaxin Xie, Yunlong Lin 等

Recently, deep learning-based pan-sharpening algorithms have achieved notable advancements over traditional methods. However, deep learning-based methods incur substantial computational overhead during inference, especially with large images. This excessive computational demand limits the applicability of these methods in real-world scenarios, particularly in the absence of dedicated computing devices such as GPUs and TPUs. To address these challenges, we propose Pan-LUT, a novel learnable look-up table (LUT) framework for pan-sharpening that strikes a balance between performance and computational efficiency for large remote sensing images. Our method makes it possible to process 15K$\times$15K remote sensing images on a 24GB GPU. To finely control the spectral transformation, we devise the PAN-guided look-up table (PGLUT) for channel-wise spectral mapping. To effectively capture fine-grained spatial details, we introduce the spatial details look-up table (SDLUT). Furthermore, to adaptively aggregate channel information for generating high-resolution multispectral images, we design an adaptive output look-up table (AOLUT). Our model contains fewer than 700K parameters and processes a 9K$\times$9K image in under 1 ms using one RTX 2080 Ti GPU, demonstrating significantly faster performance compared to other methods. Experiments reveal that Pan-LUT efficiently processes large remote sensing images in a lightweight manner, bridging the gap to real-world applications. Furthermore, our model surpasses SOTA methods in full-resolution scenes under real-world conditions, highlighting its effectiveness and efficiency.

Zhenwen Liang, Linfeng Song, Yang Li, TAO YANG, Haitao Mi, Dong Yu

Automated Theorem Proving (ATP) in formal languages remains a formidable challenge in AI, demanding rigorous logical deduction and navigating vast search spaces. While large language models (LLMs) have shown promising performance, existing stepwise provers often suffer from biased search guidance, leading to inefficiencies and suboptimal proof strategies. This paper introduces the Multi-Perspective Search Prover (MPS-Prover), a novel stepwise ATP system designed to overcome these limitations. MPS-Prover incorporates two key innovations: a highly effective post-training data curation strategy that prunes approximately 40\% of redundant training data without sacrificing performance, and a multi-perspective tree search mechanism. This search integrates a learned critic model with strategically designed heuristic rules to diversify tactic selection, prevent getting trapped in unproductive states, and enhance search robustness. Extensive evaluations demonstrate that MPS-Prover achieves state-of-the-art performance on multiple challenging benchmarks, including miniF2F and ProofNet, outperforming prior 7B parameter models. Furthermore, our analyses reveal that MPS-Prover generates significantly shorter and more diverse proofs compared to existing stepwise and whole-proof methods, highlighting its efficiency and efficacy. Our work advances the capabilities of LLM-based formal reasoning and offers a robust framework and a comprehensive analysis for developing more powerful theorem provers.

Applications · Language, Speech and Dialog

Shun Lei, Yaoxun XU, ZhiweiLin, Huaicheng Zhang, Wei tan, Hangting Chen, Yixuan Zhang, Chenyu Yang, Haina Zhu, Shuai Wang 等

Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of songs and the scarcity of high-quality data, leading to limitations in audio quality, musicality, instruction following, and vocal-instrument harmony. To address these challenges, we introduce LeVo, a language model based framework consisting of LeLM and Music Codec. LeLM is capable of parallel modeling of two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve better vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. It employs two decoder-only transformers and a modular extension training strategy to prevent interference between different token types. To further enhance musicality and instruction following ability, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO). This method handles diverse human preferences through a semi-automatic data construction process and post-training. Experimental results demonstrate that LeVo significantly outperforms existing open-source methods in both objective and subjective metrics, while performing competitively with industry systems. Ablation studies further justify the effectiveness of our designs. Audio examples and source code are available at https://levo-demo.github.io and https://github.com/tencent-ailab/songgeneration.

Applications · Language, Speech and Dialog

Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, ZhouYijie, Chenzheng Zhu, Haofen Wang, Jeff Pan, Wen Zhang, Huajun Chen 等

Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex multi-hop questions requiring multiple retrieval steps. We propose ReSearch, a novel framework that trains LLMs to Reason with Search via reinforcement learning without using any supervised data on reasoning steps. Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking, and search results subsequently influence further reasoning. We train ReSearch on Qwen2.5-7B(-Instruct) and Qwen2.5-32B(-Instruct) models and conduct extensive experiments. Despite being trained on only one dataset, our models demonstrate strong generalizability across various benchmarks. Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction during the reinforcement learning process.

Deep Learning · Everything Else

Wenfang Sun, Xinyuan Song, Pengxiang Li, Lu Yin, Yefeng Zheng, Shiwei Liu

In this paper, we re-introduce the Curse of Depth, a concept that re-introduces, explains, and addresses the recent observation in modern Large Language Models (LLMs) where deeper layers are much less effective than expected. We first confirm the wide existence of this phenomenon across the most popular families of LLMs, such as Llama, Mistral, DeepSeek, and Qwen. Our analysis, theoretically and empirically, identifies that the underlying reason for the ineffectiveness of deep layers in LLMs is the widespread usage of Pre-Layer Normalization (Pre-LN). While Pre-LN stabilizes the training of Transformer LLMs, its output variance exponentially grows with the model depth, which undesirably causes the derivative of the deep Transformer blocks to be an identity matrix, and therefore barely contributes to the training. To resolve this training pitfall, we propose LayerNorm Scaling, which scales the variance of output of the layer normalization inversely by the square root of its depth. This simple modification mitigates the output variance explosion of deeper Transformer layers, improving their contribution. Our experimental results, spanning model sizes from 130M to 7B, demonstrate that \ours significantly enhances LLM pre-training performance compared to Pre-LN. Moreover, this improvement seamlessly carries over to supervised fine-tuning. All these gains can be attributed to the fact that LayerNorm Scaling enables deeper layers to contribute more effectively during training.

Computer Vision · Image and Video Generation

Zujin Guo, Size Wu, Zhongang Cai, Wei Li, Chen Change Loy

Existing interpolation methods use pre‑trained video diffusion priors to generate intermediate frames between sparsely sampled keyframes. In the absence of 3D geometric guidance, these methods struggle to produce plausible results for complex, articulated human motions and offer limited control over the synthesized dynamics. In this paper, we introduce PoseFuse3D Keyframe Interpolator (PoseFuse3D-KI), a novel framework that integrates 3D human guidance signals into the diffusion process for Controllable Human-centric Keyframe Interpolation (CHKI). To provide rich spatial and structural cues for interpolation, our PoseFuse3D, a 3D‑informed control model, features a novel SMPL‑X encoder that encodes and aggregates 3D geometry and shape into the 2D latent conditioning space, alongside a fusion network that integrates these 3D cues with 2D pose embeddings. For evaluation, we build CHKI-Video, a new dataset annotated with both 2D poses and 3D SMPL‑X parameters. We show that PoseFuse3D-KI consistently outperforms state-of-the-art baselines on CHKI-Video, achieving a 9\% improvement in PSNR and a 38\% reduction in LPIPS. Comprehensive ablations demonstrate that our PoseFuse3D model improves interpolation fidelity.

Deep Learning · Everything Else

Sheng Wu, Lin Jin, Hui Feng, Bo Hu

Event cameras offer unique advantages in scenarios involving high speed, low light, and high dynamic range, yet their asynchronous and sparse nature poses significant challenges to efficient spatiotemporal representation learning. Specifically, despite notable progress in the field, effectively modeling the full spatiotemporal context, selectively attending to salient dynamic regions, and robustly adapting to the variable density and dynamic nature of event data remain key challenges. Motivated by these challenges, this paper proposes EventMG, a lightweight, efficient, multilevel Mamba-Graph architecture designed for learning high-quality spatiotemporal event representations. EventMG employs a multilevel approach, jointly modeling information at the micro (single event) and macro (event cluster) levels to comprehensively capture the multi-scale characteristics of event data. At the micro-level, it focuses on spatiotemporal details, employing State Space Model (SSM) based Mamba, to precisely capture long-range dependencies among numerous event nodes. Concurrently, at the macro-level, Component Graphs are introduced to efficiently encode the local semantics and global topology of dense event regions. Furthermore, to better accommodate the dynamic and sparse characteristics of data, we propose the Spatiotemporal-aware Event Scanning Technology (SEST), integrating the Adaptive Perturbation Network (APN) and Multidirectional Scanning Module (MSM), which substantially enhances the model's ability to perceive and focus on key spatiotemporal patterns. By employing this novel collaborative paradigm, EventMG demonstrates the ability to effectively capture multi-level spatiotemporal characteristics of event data while maintaining a low parameter count and linear computational complexity, suggesting a promising direction for event representation learning.

Deep Learning · Theory

Awni Altabaa, Omar Montasser, John Lafferty

Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples. Chain-of-thought (CoT) supervision, which augments training data with intermediate reasoning steps to provide a richer learning signal, has driven recent advances in large language model reasoning. This paper develops a statistical theory of learning under CoT supervision. Central to the theory is the *CoT information*, which measures the additional discriminative power offered by the chain-of-thought for distinguishing hypotheses with different end-to-end behaviors. The main theoretical results demonstrate how CoT supervision can yield significantly faster learning rates compared to standard end-to-end supervision, with both upper bounds and information-theoretic lower bounds characterized by the CoT information.

General Machine Learning · Causality

Qinwei Yang, Jingyi Li, Peng Wu

Randomized controlled trials (RCTs) often exhibit limited inferential efficiency in estimating treatment effects due to small sample sizes. In recent years, the combination of external controls has gained increasing attention as a means of improving the efficiency of RCTs. However, external controls are not always comparable to RCTs, and direct borrowing without careful evaluation can introduce substantial bias and reduce the efficiency of treatment effect estimation. In this paper, we propose a novel influence-based adaptive sample borrowing approach that effectively quantifies the "comparability'' of each sample in the external controls using influence function theory. Given a selected set of borrowed external controls, we further derive a semiparametric efficient estimator under an exchangeability assumption. Recognizing that the exchangeability assumption may not hold for all possible borrowing sets, we conduct a detailed analysis of the asymptotic bias and variance of the proposed estimator under violations of exchangeability. Building on this bias-variance trade-off, we further develop a data-driven approach to select the optimal subset of external controls for borrowing. Extensive simulations and real-world applications demonstrate that the proposed approach significantly enhances treatment effect estimation efficiency in RCTs, outperforming existing approaches.

Theory · Reinforcement Learning and Planning

Navdeep Kumar, Priyank Agrawal, Giorgia Ramponi, Kfir Y. Levy, Shie Mannor

We analyze the global convergence of the single-timescale actor-critic (AC) algorithm for the infinite-horizon discounted Markov Decision Processes (MDPs) with finite state spaces. To this end, we introduce an elegant analytical framework for handling complex, coupled recursions inherent in the algorithm. Leveraging this framework, we establish that the algorithm converges to an $\epsilon$-close \textbf{globally optimal} policy with a sample complexity of $ O(\epsilon^{-3}) $. This significantly improves upon the existing complexity of $O(\epsilon^{-2})$ to achieve $\epsilon$-close \textbf{stationary policy}, which is equivalent to the complexity of $O(\epsilon^{-4})$ to achieve $\epsilon$-close \textbf{globally optimal} policy using gradient domination lemma. Furthermore, we demonstrate that to achieve this improvement, the step sizes for both the actor and critic must decay as $ O(k^{-\frac{2}{3}}) $ with iteration $k$, diverging from the conventional $O(k^{-\frac{1}{2}}) $ rates commonly used in (non)convex optimization.

Deep Learning · Attention Mechanisms

Valeria Ruscio, Umberto Nanni, Fabrizio Silvestri

Attention sink (AS) is a consistent pattern in transformer attention maps where certain tokens (often special tokens or positional anchors) disproportionately attract attention from other tokens. We show that in transformers, AS is not an architectural artifact, but it is the manifestation of a fundamental geometric principle: the establishment of reference frames that anchor representational spaces. We analyze several architectures and identify three distinct reference frame types, centralized, distributed, and bidirectional, that correlate with the attention sink phenomenon. We show that they emerge during the earliest stages of training as optimal solutions to the problem of establishing stable coordinate systems in high-dimensional spaces. We show the influence of architecture components, particularly position encoding implementations, on the specific type of reference frame. This perspective transforms our understanding of transformer attention mechanisms and provides insights for both architecture design and the relationship with AS.

Applications · Robotics

Rui Liu, Yu Shen, Peng Gao, Pratap Tokekar, Ming C. Lin

Multi-modal learning has emerged as a key technique for improving performance across domains such as autonomous driving, robotics, and reasoning. However, in certain scenarios, particularly in resource-constrained environments, some modalities available during training may be absent during inference. While existing frameworks effectively utilize multiple data sources during training and enable inference with reduced modalities, they are primarily designed for single-agent settings. This poses a critical limitation in dynamic environments such as connected autonomous vehicles (CAV), where incomplete data coverage can lead to decision-making blind spots. Conversely, some works explore multi-agent collaboration but without addressing missing modality at test time. To overcome these limitations, we propose Collaborative Auxiliary Modality Learning (CAML), a novel multi-modal multi-agent framework that enables agents to collaborate and share multi-modal data during training, while allowing inference with reduced modalities during testing. Experimental results in collaborative decision-making for CAV in accident-prone scenarios demonstrate that CAML achieves up to a 58.1% improvement in accident detection. Additionally, we validate CAML on real-world aerial-ground robot data for collaborative semantic segmentation, achieving up to a 10.6% improvement in mIoU.

Reinforcement Learning · Deep RL

Yigit Korkmaz, Urvi Bhuwania, Ayush Jain, Erdem Bıyık

Value-based algorithms are a cornerstone of off-policy reinforcement learning due to their simplicity and training stability. However, their use has traditionally been restricted to discrete action spaces, as they rely on estimating Q-values for individual state-action pairs. In continuous action spaces, evaluating the Q-value over the entire action space becomes computationally infeasible. To address this, actor-critic methods are typically employed, where a critic is trained on off-policy data to estimate Q-values, and an actor is trained to maximize the critic's output. Despite their popularity, these methods often suffer from instability during training. In this work, we propose a purely value-based framework for continuous control that revisits structural maximization of Q-functions, introducing a set of key architectural and algorithmic choices to enable efficient and stable learning. We evaluate the proposed actor-free Q-learning approach on a range of standard simulation tasks, demonstrating performance and sample-efficiency on par with state-of-the-art baselines, without the cost of learning a separate actor. Particularly, in environments with constrained action spaces, where the value functions are typically non-smooth, our method with structural maximization outperforms traditional actor-critic methods with gradient-based maximization.

Reinforcement Learning · Deep RL

Yunpeng Jiang, Jianshu Hu, Paul Weng, Yutong Ban

Symmetry is pervasive in robotics and has been widely exploited to improve sample efficiency in deep reinforcement learning (DRL). However, existing approaches primarily focus on spatial symmetries—such as reflection, rotation, and translation—while largely neglecting temporal symmetries. To address this gap, we explore time reversal symmetry, a form of temporal symmetry commonly found in robotics tasks such as door opening and closing. We propose Time Reversal symmetry enhanced Deep Reinforcement Learning (TR-DRL), a framework that combines trajectory reversal augmentation and time reversal guided reward shaping to efficiently solve temporally symmetric tasks. Our method generates reversed transitions from fully reversible transitions, identified by a proposed dynamics-consistent filter, to augment the training data. For partially reversible transitions, we apply reward shaping to guide learning, according to successful trajectories from the reversed task. Extensive experiments on the Robosuite and MetaWorld benchmarks demonstrate that TR-DRL is effective in both single-task and multi-task settings, achieving higher sample efficiency and stronger final performance compared to baseline methods.

Theory · Learning Theory

Baoquan Gong, Xiyuan Gao, Pengfei Zhu, Qinghua Hu, Bing Cao

Multimodal learning systems often encounter challenges related to modality imbalance, where a dominant modality may overshadow others, thereby hindering the learning of weak modalities. Conventional approaches often force weak modalities to align with dominant ones in "Learning to be (the same)" (Positive Learning), which risks suppressing the unique information inherent in the weak modalities. To address this challenge, we offer a new learning paradigm: "Learning Not to be" (Negative Learning). Instead of enhancing weak modalities’ target-class predictions, the dominant modalities dynamically guide the weak modality to suppress non-target classes. This stabilizes the decision space and preserves modality-specific information, allowing weak modalities to preserve unique information without being over-aligned. We proceed to reveal the multimodal learning from a robustness perspective and theoretically derive the Multimodal Negative Learning (MNL) framework, which introduces a dynamic guidance mechanism tailored for negative learning. Our method provably tightens the robustness lower bound of multimodal learning by increasing the Unimodal Confidence Margin (UCoM) and reduces the empirical error of weak modalities, particularly under noisy and imbalanced scenarios. Extensive experiments across multiple benchmarks demonstrate the effectiveness and generalizability of our approach against the competing methods. The code will be available at: https://github.com/BaoquanGong/Multimodal-Negative-Learning.git

Deep Learning · Algorithms

Saleh Ashkboos, Mahdi Nikdan, Rush Tabesh, Roberto Castro, Torsten Hoefler, Dan Alistarh

Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning pre-trained models, which can have large weight, activation, and error (output gradient) outlier values that make lower-precision optimization difficult. To address this, we present HALO, a new quantization-aware training approach for Transformers that enables accurate and efficient low-precision training by combining 1) strategic placement of Hadamard rotations in both forward and backward passes, which mitigate outliers, 2) high-performance kernel support, and 3) FSDP integration for low-precision communication. Our approach ensures that all large matrix multiplications during the forward and backward passes are executed in lower precision. Applied to LLaMa models, HALO achieves near-full-precision-equivalent results during fine-tuning on various tasks, while delivering up to 1.41x end-to-end speedup for full fine-tuning on RTX 4090 GPUs. HALO efficiently supports both standard and parameter-efficient fine-tuning (PEFT). Our results demonstrate the first practical approach to fully quantized LLM fine-tuning that maintains accuracy in INT8 and FP6 precision, while delivering performance benefits.

Computer Vision · Everything Else

Sungmin Woo, Sangyoun Lee

Depth-from-Focus (DFF) enables precise depth estimation by analyzing focus cues across a stack of images captured at varying focal lengths. While recent learning-based approaches have advanced this field, they often struggle in complex scenes with fine textures or abrupt depth changes, where focus cues may become ambiguous or misleading. We present DualFocus, a novel DFF framework that leverages the focal stack’s unique gradient patterns induced by focus variation, jointly modeling focus changes over spatial and focal dimensions. Our approach introduces a variational formulation with dual constraints tailored to DFF: spatial constraints exploit gradient pattern changes across focus levels to distinguish true depth edges from texture artifacts, while focal constraints enforce unimodal, monotonic focus probabilities aligned with physical focus behavior. These inductive biases improve robustness and accuracy in challenging regions. Comprehensive experiments on four public datasets demonstrate that DualFocus consistently outperforms state-of-the-art methods in both depth accuracy and perceptual quality.

Reinforcement Learning · Everything Else

Xuyuan Xiong, Pedro Chumpitaz-Flores, Kaixun Hua, Cheng Hua

Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method for computing decision tree policies, which formulates the optimization problem as a mixed-integer linear program (MILP). To enhance efficiency, we employ a reduced-space branch-and-bound approach that decouples the MDP dynamics from tree-structure constraints, enabling efficient parallel search. This significantly improves runtime and scalability compared to previous methods. Our approach ensures that each iteration yields the optimal decision tree. Experimental results on standard benchmarks demonstrate that SPOT achieves substantial speedup and scales to larger MDPs with a significantly higher number of states. The resulting decision tree policies are interpretable and compact, maintaining transparency without compromising performance. These results demonstrate that our approach simultaneously achieves interpretability and scalability, delivering high-quality policies an order of magnitude faster than existing approaches.

Reinforcement Learning · Deep RL

Liyuan Mao, Haoran Xu, Amy Zhang, Weinan Zhang, Chenjia Bai

Obtaining a generalizable reward model is crucial in Reinforcement Learning from Human Feedback (RLHF) as it enables correctly evaluating unseen prompt-response pairs. However, existing reward models lack this ability, as they are typically trained by increasing the reward gap between chosen and rejected responses, while overlooking the prompts that the responses are conditioned on. Consequently, when the trained reward model is evaluated on prompt-response pairs that lie outside the data distribution, neglecting the effect of prompts may result in poor generalization of the reward model. To address this issue, we decompose the reward value into two independent components: prompt-free reward and prompt-related reward. Prompt-free reward represents the evaluation that is determined only by responses, while the prompt-related reward reflects the reward that derives from both the prompt and the response. We extract these two components from an information theoretical perspective, which requires no extra models.. Subsequently, we propose a new reward learning algorithm by prioritizing data samples based on their prompt-free reward values. Through toy examples, we demonstrate that the extracted prompt-free and prompt-related rewards effectively characterize two parts of the reward model. Further, standard evaluations show that our method improves both the alignment performance and the generalization capability of the reward model.

Applications · Time Series

Hui Chen, Vikas Singh

Diffusion models have achieved significant success, yet their application to time series data, particularly with regard to efficient sampling, remains an active area of research. We describe an operator-learning approach for conditioned time-series diffusion models that gives efficient single-step generation by leveraging insights from the frequency-domain characteristics of both the time-series data and the diffusion process itself. The forward diffusion process induces a structured, frequency-dependent smoothing of the data's probability density function. However, this frequency smoothing is related (e.g., via likelihood function) to easily accessible frequency components of time-series data. This suggests that a module operating in the frequency space of the time-series can, potentially, more effectively learn to reverse the frequency-dependent smoothing of the data distribution induced by the diffusion process. We set up an operator learning task, based on frequency-aware building blocks, which satisfies semi-group properties, while exploiting the structure of time-series data. Evaluations on multiple datasets show that our single-step generation proposal achieves forecasting/imputation results comparable (or superior) to many multi-step diffusion schemes while significantly reducing inference costs.