跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 06:21 — 2026-11-19 06:21(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 19 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2507.14845

Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Image

Rizhao Fan, Zhigen Li, Heping Li, Ning An

原文摘要

Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse measurements remains a challenging problem. Supervised learning methods rely on dense depth labels to predict unobserved regions, while self-supervised approaches require image sequences to enforce geometric constraints and photometric consistency between frames. However, acquiring dense annotations is costly, and multi-frame dependencies limit the applicability of self-supervised methods in static or single-frame scenarios. To address these challenges, we propose a novel self-supervised depth completion paradigm that requires only sparse depth measurements and their corresponding image for training. Unlike existing methods, our approach eliminates the need for dense depth labels or additional images captured from neighboring viewpoints. By leveraging the characteristics of depth distribution, we design novel loss functions that effectively propagate depth information from observed points to unobserved regions. Additionally, we incorporate segmentation maps generated by vision foundation models to further enhance depth estimation. Extensive experiments demonstrate the effectiveness of our proposed method.

cs.CV

版本更新 · v3arXiv:2312.10181

Integrating Fairness and Model Pruning Through Bi-level Optimization

Yucong Dai, Gen Li, Feng Luo, Xiaolong Ma, Yongkai Wu

原文摘要

Deep neural networks achieve high predictive performance but often require substantial computational and storage resources, which motivates model compression techniques such as neural network pruning. Conventional pruning methods, however, can introduce or amplify algorithmic bias and produce disparate outcomes across demographic groups. We study fair model pruning, which seeks sparse models that satisfy fairness criteria while maintaining predictive performance. We characterize fairness using both group accuracy disparity and differences in compression-induced accuracy degradation across demographic groups. We propose a framework that jointly optimizes pruning masks and model weights under fairness constraints, thereby integrating accuracy and fairness into the compression process. We formulate fair pruning as a constrained bi-level optimization problem and derive an efficient optimization procedure. Experiments across multiple datasets, predictive tasks, model architectures, and sparsity levels show that our framework improves the trade-off among fairness, accuracy, and training efficiency relative to the baseline pruning strategies. Compared with the strongest evaluated baselines, BiFP maintains competitive accuracy and fairness while requiring more than 94% fewer training iterations in the real-world experiments.

cs.LG · cs.AI · cs.CY

版本更新 · v2arXiv:2610.34128

Semantic-Coupled Perception Framework for Autonomous Laparoscope Control

Enduo Zhao, Fangzhou Li, Yujie Zhu, Sicheng Lu, Fang Chen, Longfei Ma, Hongen Liao

原文摘要

In minimally invasive surgery (MIS), maintaining an appropriate field of view (FoV) is essential for surgical safety and efficiency. However, conventional autonomous laparoscope control methods often treat visual tracking and surgical phase recognition independently, limiting robustness under occlusion, entity overlap, and camera motion. This paper proposes a closed-loop autonomous laparoscope control framework that couples real-time surgical phase recognition with camera-motion-compensated visual perception. By exploiting phase-dependent relationships among surgical entities, the framework improves target state estimation under challenging visual conditions, supporting task-aware autonomous FoV control. Benchmark and phantom experiments evaluate the framework in surgical phase recognition, target tracking under occlusion and entity overlap, and autonomous FoV control, showing improved target visibility and task execution compared with fixed-FoV control. These results highlight the potential of incorporating task-level semantics into visual state estimation for autonomous laparoscope guidance.

cs.RO · eess.SY

新论文 · v1arXiv:2611.16159

From Tokens to Behaviors: Rethinking Generative Recommendation for User Trajectory Prediction

Jiaqi Wang, Hanchen Yang, Hengyu Zhang, Hongxu Ma, Wenqi Rao, Hongyang Wang, Zhongbo Sun, Renliang Qian 等 15 位作者

原文摘要

User behavior trajectory prediction (UBTP) aims to capture how a user's needs evolve over time by predicting the sequence of future interactions from that user's interaction history. Recent generative recommendation (GR) methods address this task through autoregressive generation of semantic IDs (SIDs). However, serial SID decoding couples token generation with behavior state transitions and requires multiple dependent steps per interaction. Discrete item feedback overlooks predictive uncertainty, and teacher-forced training leaves a training-inference gap in trajectory generation. To address these limitations, we propose TraGR, a behavior-aware generative recommendation framework that aligns generation, feedback, and learning with successive user behaviors. Its behavior-level architecture predicts SID tokens in parallel within each interaction and models behavioral transitions through recurrent state updates, with joint SID and item-level supervision. Probability feedback combines the selected behavior with a probability-weighted summary of alternatives to guide subsequent predictions. Relation-aware trajectory learning incorporates collaborative transition signals and later credit assignment into training on model-generated trajectories. Experiments on four public datasets demonstrate that TraGR consistently outperforms state-of-the-art baselines across different prediction horizons. Code: https://github.com/CalmaQi/GR4UBT.

cs.IR

新论文 · v1arXiv:2611.14922

A Transferable Pretrained 3D Model for Impedance Inversion with Sparse-Well Prior Conditioning

Gen Li, Zhaoyun Zong, Diqiong Jiang, Man Tang

原文摘要

Deep-learning-based seismic impedance inversion commonly requires retraining for each target survey, which may generalize poorly beyond the conditioning locations when well control is extremely sparse. We propose a transferable three-dimensional inversion framework that separates offline learning from target-survey deployment. A masked autoencoder first learns seismic structural representations from unlabeled multi-survey data, after which the frozen encoder is incorporated into an inversion network trained on synthetic geological models with sparse-well-derived low-frequency priors. During deployment, the complete inversion network remains fixed; the available conditioning well is used only to construct the low-frequency prior and align the global impedance range. Experiments on the Overthrust model show that the proposed method achieves the lowest full-volume NRMSE and reduces the P95 trace-wise NRMSE from 0.1310 to 0.1074 relative to the best target-trained baseline, indicating fewer localized large errors under different well locations. In a field survey with one conditioning well and three blind wells, it reduces the mean blind-well NRMSE by 20.95% relative to the target-trained U-Net while maintaining the highest correlation. These results demonstrate that the proposed framework transfers useful impedance information beyond the conditioning location with low deployment cost and without retraining the inversion network.

cs.LG · physics.geo-ph

新论文 · v1arXiv:2611.14328

前向值离散化:无需高阶近似的高效随机扩散采样

Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation

Yuchen Jiao, Na Li, Changxiao Cai, Yuting Wei, Gen Li

AI 速读 基于摘要

作者提出免训练的前向值离散化框架,通过在基于历史预测构造的前瞻点上评估模型,在保持一阶收敛的同时改善随机扩散采样的采样效率。

cs.LG · cs.AI · stat.ML

查看原文摘要

Stochastic diffusion samplers often require substantially more neural function evaluations (NFEs) than deterministic samplers to achieve comparable sample quality. Although higher-order discretization accelerates deterministic sampling, its benefits for stochastic sampling remains unclear. We establish matching upper and worst-case lower bounds showing that stochastic samplers with higher-order approximations remain first-order convergent, even with exact score functions. Thus, increasing the approximation order does not generally improve the convergence order. Motivated by this limitation, we introduce forward-value discretization, a training-free framework that evaluates the data/noise prediction model at a lookahead estimate constructed from previous predictions. For deterministic sampling, the resulting Forward DPMSolver (F-DPMSolver), improves sample quality at low NFE budgets through its DDIM-based variant, despite remaining first-order convergent. For stochastic sampling, we develop Forward DDPM (F-DDPM), which evaluates the model at a cleaner lookahead point adjusted for subsequent noise injection. This estimate reuses both the previous model prediction and the previously injected noise. Both variants admit first-order convergence guarantees with one model evaluation per iteration. Across CIFAR-10, ImageNet, FFHQ, and LSUN, F-DDPM consistently achieves lower FID than the evaluated stochastic baselines at matched NFE budgets. With 1.5 times as many NFEs as deterministic baselines, it achieves competitive sample quality, narrowing the practical efficiency gap between stochastic and deterministic sampling. Code is available at https://github.com/Na-Li66/F-DDPM.

新论文 · v1arXiv:2611.11503

AgentCT: A Vision-Language Agent for Universal CT Imaging

Zhihao Chen, Qi Gao, Chuang Niu, Qiegen Liu, Yi Zhang, Hongming Shan

原文摘要

Computed tomography (CT) restoration methods often use a single network for low-dose CT (LDCT), sparse-view CT (SVCT), and metal artifact reduction (MAR), despite the distinct physics of these degradations. We propose AgentCT, a vision-language agent that identifies the degradation and routes images to task-specific restoration models. A LoRA-adapted Qwen3-VL-4B controller predicts degradation type and severity, selects a specialist, and reassesses the restored image. The LDCT specialist uses an image-domain diffusion model, whereas the SVCT and MAR specialists combine projection-domain correction, data consistency, differentiable filtered back-projection, and image refinement. We evaluated the controller and specialists separately on patient-disjoint Mayo 2020 abdominal CT data across three severity levels for each degradation. The controller achieved 95.7% accuracy for degradation type and 93.9% for severity, with a 100% JSON parse rate. Using ground-truth degradation labels for routing, AgentCT achieved an overall PSNR/SSIM of 46.18 dB/0.984, compared with 44.93 dB/0.976 for AMIR and 44.29 dB/0.979 for TAMP, and attained the highest PSNR in all nine settings. For SVCT, its dual-domain specialist achieved 46.04 dB with 4.2 million parameters, compared with 44.43 dB for single-task AMIR and 43.57 dB for all-in-one AMIR with 23.5 million parameters. These results support degradation-specific CT restoration with controller-based model selection; evaluation under automatic routing and on independent clinical data remains necessary. Code is available at https://github.com/hao1635/AgentCT.

cs.CV

版本更新 · v3arXiv:2606.04627

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

Zhichao Yang, Yuanze Hu, Haojie Hao, Longkun Hao, Dongshuo Huang, Hongyu Lin, Gen Li, Lanqing Hong 等 10 位作者

原文摘要

Mobile agents are increasingly expected to operate everyday applications from screenshots and language goals, where reliable control requires reasoning over screen affordances, multi-step navigation, and future state changes. However, many agents externalize this computation as long textual chains of thought, which slows interaction, increases supervision cost, and complicates deployment. We introduce MIRAGE, a framework that learns continuous latent reasoning representations from visible textual reasoning traces. MIRAGE transfers explicit reasoning into compact hidden states, enabling the agent to reason internally without decoding long rationales. It also incorporates a generative world-model objective: latent reasoning vectors are aligned with future screenshots, encouraging the agent to anticipate upcoming interface states before acting. This turns hidden computation into both a compressed thought representation and a forward-looking model of environment dynamics. At inference time, MIRAGE reasons in continuous latent space, reducing token generation while improving execution efficiency. On AndroidWorld, MIRAGE matches explicit chain-of-thought supervised fine-tuning in the 4B ablation with a 3-5x lower decoded-token budget and improves a comparable instruction-tuned baseline by 10.2 points; on AndroidControl, it improves action grounding while generating over 75% fewer tokens.

cs.AI

版本更新 · v3arXiv:2401.08739

EgoGen: An Egocentric Synthetic Data Generator

Gen Li, Kaifeng Zhao, Siwei Zhang, Xiaozhong Lyu, Mihai Dusmanu, Yan Zhang, Marc Pollefeys, Siyu Tang

原文摘要

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered third-person-view vision models, but its application to embodied egocentric perception tasks remains largely unexplored. A critical challenge lies in simulating natural human movements and behaviors that effectively steer the embodied cameras to capture a faithful egocentric representation of the 3D world. To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. Combined with collision-avoiding motion primitives and a two-stage reinforcement learning approach, our motion synthesis model offers a closed-loop solution where the embodied perception and movement of the virtual human are seamlessly coupled. Compared to previous works, our model eliminates the need for a pre-defined global path, and is directly applicable to dynamic environments. Combined with our easy-to-use and scalable data generation pipeline, we demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views. EgoGen will be fully open-sourced, offering a practical solution for creating realistic egocentric training data and aiming to serve as a useful tool for egocentric computer vision research. Refer to our project page: https://ego-gen.github.io/.

cs.CV · cs.AI

版本更新 · v4arXiv:2506.07886

EgoM2P: Egocentric Multimodal Multitask Pretraining

Gen Li, Yutong Chen, Yiqian Wu, Kaifeng Zhao, Marc Pollefeys, Siyu Tang

原文摘要

Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction, enabling systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mounted camera trajectories, is often infeasible, making standard supervised learning approaches difficult to scale. Furthermore, dynamic camera motion and the complex temporal and spatial structure of first-person video pose additional challenges for the direct application of existing multimodal foundation models. To address these challenges, we introduce a set of efficient temporal tokenizers and propose EgoM2P, a masked modeling framework that learns from temporally-aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding. This unified design supports multitasking across diverse egocentric perception and synthesis tasks, including gaze prediction, egocentric camera tracking, and monocular depth estimation from egocentric video, and also serves as a generative model for conditional egocentric video synthesis. Across these tasks, EgoM2P matches or outperforms specialist models while being an order of magnitude faster. We will fully open-source EgoM2P to support the community and advance egocentric vision research. Project page: https://egom2p.github.io/.

cs.CV

版本更新 · v2arXiv:2604.23239

AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting

Xudong Jiang, Mingshan Loo, Wengen Li, Mingrui Zhang, Jihong Guan, Shuigeng Zhou

原文摘要

Time-series forecasting is foundational to a wide spectrum of web-scale services, spanning personalized recommendations, energy scheduling, and infrastructure capacity planning. Accurate long-term time series forecasting (LTSF) requires models to capture long-range temporal dependencies while adapting to periodic patterns that vary across variables. Although frequency-aware methods offer a global view of temporal dynamics, they typically rely on inflexible heuristic designs, such as predefined period lengths, manually selected or randomly sampled top-k frequency components, and separate spectral transformations. Consequently, they fail to account for time-frequency heterogeneity, where variables that appear synchronized in the time domain can differ substantially in the frequency domain. Meanwhile, Mamba-based forecasters, despite their efficiency in long-range modeling, introduce frequency information only as auxiliary signals, leaving spectral evidence disconnected from state transitions. In this work, we propose AdaMamba, a novel approach that explicitly internalizes input-dependent frequency information into the modeling of temporal dependencies. AdaMamba comprises an interaction learning module and an adaptive frequency-gated state space module: the former captures cross-variable dependencies and multi-scale temporal context, while the latter generates context-dependent frequency bases and unifies temporal forgetting into a single time-frequency gate that directly modulates state evolution. Extensive experiments on seven public LTSF benchmarks and four domain-specific datasets demonstrate that AdaMamba consistently outperforms state-of-the-art baselines while maintaining competitive computational efficiency.

cs.AI

新论文 · v1arXiv:2611.03126

CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements

Xinlei Yu, Gen Li, Ji Zhao, Zhangquan Chen, Congcong Wang, Shuai Dong, Zelin Peng, Yuqi Xu 等 18 位作者

原文摘要

Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested double-loop recursive improvement framework. At the system level, an outer world-data-model flywheel continuously incorporates open-world corpus and leverages evolving model weaknesses to guide subsequent data construction and optimization iterations. At the data level, an inner flywheel couples open-world seeding and autocatalytic propagation. The former mines authentic workflows as seed tasks from instructional videos, and employs visual-semantic dual-path trajectory reconstruction; The latter transforms these seeds into reusable primitives for controllable synthesis of diverse, complex, and verifiable tasks. To enable efficient and reliable trajectory collection, we further introduce a feedback-guided snapshot-rollback retry mechanism in various real environments. Extensive experiments demonstrate that CUA-Master-27B achieves competitive performance across GUI-only and GUI-CLI hybrid benchmarks, scoring 80.2 on OSWorld Verified, 36.9 on OSWorld 2.0, 43.9 on WeaveBench, and 25.0 on Agents' Last Exam. Our framework also substantially improves the quality and efficiency of data synthesis, and exhibits continuous gains across recursive iterations.

cs.AI

新论文 · v1arXiv:2610.40276

TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents

Guangzhi Wang, Junfu Pu, Yiran Wang, Xingyilang Yin, Honghao Chen, Cheng Cheng, Lingen Li, Yinan Zhou 等 13 位作者

原文摘要

Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor models with substantially different computational profiles, making them difficult to realize within a single model. In this work, we present TaskFrame, a hierarchical planner-controller framework that connects task-level planning with frame-level keyboard-and-mouse control. A vision-language task planner decomposes a high-level goal into an ordered sequence of atomic instructions and is optimized through supervised learning and dependency-aware GRPO. The hidden states of special goal tokens that terminate each atomic instruction provide continuous goal embeddings that are cached and reused across control steps. A causal Transformer controller combines the embedding of the active goal with recent observations to predict discrete keyboard and mouse-button actions and continuous camera motion at every game step. We train the system in three stages: planner training, controller pretraining, and joint alignment. Experiments in Minecraft show that TaskFrame is competitive with general-purpose vision-language models on instruction decomposition, and that in closed-loop evaluation the agent achieves a higher combat success rate than the evaluated baselines.

cs.CV · cs.AI

新论文 · v1arXiv:2610.39114

From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion

Jiaqi Wang, Yisen Gao, Huayang Shi, Junhao Hou, Wengen Li, Jihong Guan, Yichao Zhang, Shuigeng Zhou 等 10 位作者

原文摘要

Triple set prediction (TSP) is to recover missing relational triples in a knowledge graph by predicting the triple set instead of isolated links. Existing approaches predominantly rely on the subgraph-based completion paradigm, where the original graph is first partitioned into local subgraphs which are then independently completed. Such a paradigm suffers from fragmented structural reasoning, limited cross subgraph dependency modeling, and missing predictions across subgraphs. This paper proposes LatentDiff, a novel unified latent generative framework for TSP, which reformulates knowledge graph completion as latent space graph generation. LatentDiff first learns a compact latent representation using a relation-aware residual-quantized knowledge graph autoencoder, which encodes the whole graph into relation-aware latent embeddings, quantizes them with chunked residual codebooks, and reconstructs triples through a factorized decoder. On top of this latent space, we introduce an observation-anchored latent graph diffusion model, where the target latent graph representation is perturbed toward the observed latent. The reverse process recovers missing triples through progressive latent denoising. Experiments on three benchmark datasets show that LatentDiff outperforms the SOTA in terms of F_{tsp} by 5.4 percentage points on average. Code: https://anonymous.4open.science/r/LKGDiff-44A5.

cs.LG · cs.AI

新论文 · v1arXiv:2610.35656

Provably Efficient Q-learning for Robust Reinforcement Learning

Yuchen Jiao, Gen Li

原文摘要

Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robust RL algorithms based on robust MDPs (RMDPs) have been proposed, for ensuring that agents can perform reliably to unpredictable conditions in real-world environments. Despite of the rich literature, \revision{an efficient model-free method is still lacking} for robust RL, particularly for Markovian data, which is more relevant in practical applications. In this work, we take a step towards settling this problem by proposing a sample efficient (asynchronous Q-learning) algorithm for robust RL. In particular, consider a $γ$-discounted infinite-horizon RMDP with state space $\mathcal{S}$ and action space $\mathcal{A}$, where the uncertainty set is specified by the total variation (TV) distance with uncertainty level $σ$. Assuming access to a single trajectory of Markovian samples induced by a behavior policy and the nominal transition kernel, the sample complexity of the proposed Q-learning algorithm --- to achieve an entrywise $\varepsilon$-approximation of the optimal Q-function --- is bounded by $$ \frac{1}{μ_{\mathsf{min}}\varepsilon^2(1-γ)^3\max\{1-γ,σ\}} + \frac{t_{\mathsf{mix}}}{μ_{\mathsf{min}}(1-γ)} $$ up to logarithmic factors. Here, $t_{\mathsf{mix}}$ and $μ_{\mathsf{min}}$ denote the mixing time and the minimum state-action occupancy probability of the sample trajectory, respectively. This result is nearly minimax optimal, with an additional factor of $\frac{1}{1-γ}$. Moreover, it achieves a significant improvement over existing bounds.

stat.ML · cs.AI · cs.LG · math.ST

版本更新 · v2arXiv:2608.28158

HARTS: A Prefix-Sharing Training System for Agentic RL with Hybrid-Attention Models

Boyuan Meng, Peihua Bao, Hong Liu, Xiaowei Zhu, Chao Wang, Gen Li, Zhenxuan Pan

原文摘要

Agentic reinforcement learning (RL) generates irregular rollout trees, but trajectory-by-trajectory training recomputes their shared interaction histories. Existing training-time prefix-reuse systems do not jointly address state recovery, dense execution, and distributed training for hybrid-attention models. We present HARTS (Hybrid-Attention RL over Tree Structures), to our knowledge the first system to demonstrate training acceleration from arbitrary rollout-tree prefix sharing on real hybrid-attention models. A two-level planner constructs compression-oriented microbatches, then jointly refines their membership, cross-microbatch sharing, placement, and execution order. Within each sharing window, gradients from dependent microbatches accumulate before one backward pass through the shared prefix computation. Differentiable boundary-state handoff and bounded replay preserve the per-trajectory chunkwise numerical path, while a linear-time planner attains the global minimum number of sequential linear-attention calls under our packed chunkwise-call model. The runtime uses a common compact layout across attention and dense or mixture-of-experts (MoE) layers, with support for distributed parallelism and activation recomputation. Recovering log-probabilities for each original trajectory position preserves RL objectives; for deterministic top-k routing without token dropping, occurrence counts restore MoE objective weights and expert-load statistics. On SWE-bench, HARTS delivers 4.77-10.45x the update throughput of trajectory-expanded training across two sampling schemes on 7.9B- and 124B-parameter hybrid-attention MoE models using 8-64 GPUs. On the 7.9B model, full-model logit differences are comparable to baseline self-rerun variation. The 124B model shows stable online learning trends through step 150 on SWE-bench and $τ^3$-Bench.

cs.LG · cs.DC

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1342ACL Anthology · ACL 2026

LaCo: Layer-wise Compensation for Pruned Large Language Models

Yingen Liu, Fan Wu, Panxuyan, Ruihui Li Hunan University, Zhuo Tang Hunan University, Kenli Li Hunan University

原文摘要

Pruning is essential for the efficient deployment of Large Language Models (LLMs); however, it causes severe performance degradation due to the structural distortion induced by sparsity.Existing recovery strategies, such as LoRA, predominantly employ global fine-tuning, often overlooking the mechanistic root of this degradation: the layer-wise accumulation and amplification of local errors. To address this limitation, we propose LaCo(Layer-wise Compensation), a framework that reorients the recovery paradigm from global adaptation to hierarchical representation alignment.By sequentially optimizing each layer to reconstruct the model’s hidden states, LaCo effectively intercept the error propagation chain at its source.Extensive experiments demonstrate that LaCo surpasses parameter-efficient baselines in both perplexity reduction and zero-shot reasoning.Notably, it reduces recovery-time memory usage to approximately 1/7 of the baseline and requires only 2,048 unlabeled samples to match a LoRA model trained on 50k examples—achieving a \sim25\times improvement in data efficiency.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.38ACL Anthology · ACL 2026

FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation

Gen Li Baidu, Peiyu Liu University of International Business and Economics

原文摘要

Vision–Language Models (VLMs) excel at visual reasoning but still struggle with external knowledge integration. Retrieval-Augmented Generation(RAG) is a promising solution, but current methods remain inefficient and often fail to maintain high answer quality. To address these challenges, we propose VideoSpeculateRAG, an efficient VLM-based RAG framework built on two key ideas. First, we introduce a speculative decoding pipeline: a lightweight draft model quickly generates multiple answer candidates, which are then verified and refined by a more accurate heavyweight model, substantially reducing inference latency without sacrificing correctness. Second, we identify a major source of error, incorrect entity recognition in retrieved knowledge, and mitigate it with a simple yet effective similarity-based filtering strategy that improves entity alignment and boosts overall answer accuracy. Experiments demonstrate that VideoSpeculateRAG achieves comparable or higher accuracy than standard RAG approaches, while speeding up the inference by approximately 2x. Our framework highlights the potential of combining speculative decoding with retrieval-augmented reasoning to enhance efficiency and reliability in complex, knowledge-intensive multimodal tasks.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.583ACL Anthology · ACL 2026

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Sikuan Yan Ludwig-Maximilians-Universität München and Huawei Technologies Ltd., Xiufeng Yang, Zuchao Huang, Ercong Nie Shanghai Jiaotong University, Zifeng Ding, Zonggen Li University of Hong Kong, Xiaowen Ma, Jinhe Bi 等 13 位作者

原文摘要

Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to address this limitation often augment LLMs with an external memory bank, yet most existing pipelines are static and heuristic-driven, lacking a learned mechanism for deciding what to store, update, or retrieve. We present Memory-R1, a reinforcement learning (RL) framework that equips LLMs with the ability to actively manage and utilize external memory through two specialized agents: a Memory Manager that learns structured operations, including ADD, UPDATE, DELETE, and NOOP; and an Answer Agent that pre-selects and reasons over relevant entries. Both agents are fine-tuned with outcome-driven RL (PPO and GRPO), enabling adaptive memory management with minimal supervision. With only 152 training QA pairs, Memory-R1 outperforms strong baselines and generalizes across diverse question types, three benchmarks (LoCoMo, MSC, LongMemEval), and multiple model scales (3B–14B).

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表