论文检索

Deep Learning · Large Language Models

Yushu Zhao, Zheng Wang, Minjia Zhang

Mixture-of-Experts (MoE) have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input. However, their deployment remains limited due to the high memory overhead associated with storing all expert parameters, particularly as the number of experts increases. To address this challenge, prior works have explored expert dropping and merging strategies; however, they often suffer from notable performance drop especially at high compression ratios due to their reliance on coarse-grained tensor- or expert-level operations. In this paper, we introduce PuzzleMoE, the first MoE merging method to enable fine-grained element-wise merging while achieving both high accuracy and inference speed, via two key innovations: First, PuzzleMoE performs sparse expert merging by identifying element-wise weight redundancy and specialization. It introduces a dual-mask approach to capture both shared and expert-specific salient parameters. Second, to avoid the overhead of storing masks and signs, we introduce a bit-packed encoding scheme that reuses underutilized exponent bits, enabling efficient MoE inference on GPUs. Extensive experiments demonstrate that PuzzleMoE outperforms prior MoE compression methods by up to 16.7\% on MMLU at 50\% compression ratio, and achieves up to 1.80$\times$ end-to-end inference throughput gain.

Applications · Robotics

Li Ji, Siyin Wang, Pengfang Qian, Xiaopeng Yu, Yihai Tian, Zhaoye Fei, Jingjing Gong, Xipeng Qiu

Current Vision-Language-Action (VLA) models excel at robotic manipulation but often struggle with non-Markovian tasks requiring long-term memory and reasoning due to their reliance on immediate observations. Existing solutions face a frequency-competence paradox, where high-performance models are too slow for real-time control, while faster models lack sufficient reasoning capabilities. To resolve this architectural misalignment, we propose **HiMe**, a Hierarchical Embodied Memory framework that decouples embodied intelligence into a high-frequency Executor for execution, a Sentry for working memory, and a Planner for long-term strategy. We also introduce a dynamic knowledge system based on cross-modal semantic schemas and active management mechanisms, allowing robots to maintain memory plasticity through "Add, Update, and Delete" operations. This hierarchical design effectively balances the conflict between real-time execution and slow thinking planning, significantly improving success rates in long-horizon tasks. Experiments demonstrate that this approach not only outperforms flat memory baselines but also exhibits the novel ability to self-correct its internal knowledge based on human preferences.

Qi Yu, Ruizhong Qiu, Zhichen Zeng, My T. Thai, huan liu, Hanghang Tong

Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment, whose effectiveness largely depends on sparse supervision that is hard or costly to obtain in practice. Existing works, however, largely overlook how to actively acquire high-quality supervision to improve their alignment performance under OT frameworks. In this paper, we propose a principled active alignment framework for optimal transport alignment called AvAtar. We quantify the informativeness of a candidate by measuring its gradient-based impact on the global alignment result, computed as the gradient propagation from the global alignment result to all possible supervisions of the candidate through the entropy-regularized OT formulation. While differentiating through OT is challenging given its constrained nature, we leverage the adjoint-state method to reformulate the computation to a linear system solvable by the conjugate gradient method with linear complexity and guaranteed convergence. By encoding the global alignment result via effective utility functions, AvAtar is applicable to general alignment problems under the OT framework. Extensive experiments on three representative alignment tasks demonstrate the effectiveness, scalability, and generalizability of the proposed AvAtar.

Yitian Gong, Kuangwei Chen, Zhaoye Fei, Xiaogui Yang, Ke Chen, Yang Wang, Kexin Huang, Mingshu Chen, Ruixiao Li, Qinyuan Cheng 等

Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Despite recent progress, existing approaches often rely on pretrained encoders, semantic distillation, or heterogeneous CNN-based architectures. These designs introduce fixed inductive biases that limit reconstruction fidelity and hinder effective scaling. In this paper, we argue that discrete audio tokenization should be learned fully end-to-end using a homogeneous and scalable architecture. Based on this perspective, we propose $\textbf{TAC}$, a Transformer-based audio tokenizer that jointly optimizes the encoder, quantizer, and decoder from scratch for high-fidelity reconstruction of general audio. We show that a simple, fully end-to-end learned tokenizer built from homogeneous, causal Transformer blocks scales gracefully and supports high-fidelity reconstruction across diverse audio domains. Across speech, sound, and music, the proposed tokenizer consistently outperforms prior codecs over a wide range of bitrates, while exhibiting predictable improvements with increased scale. Notably, leveraging TAC’s discrete tokens, we develop the first purely autoregressive TTS model that surpasses prior non-autoregressive and cascaded systems. Furthermore, TAC enables competitive ASR performance without auxiliary encoders. Our findings position TAC as a unified, scalable interface for the next generation of native audio foundation models.

Deep Learning · Foundation Models

Chunlei Meng, Pengbin Feng, Rong Fu, Hoi Leong Lee, Xiaojing Du, Yuying Li, Zeyu Zhang, Weilin Zhou, Chun Ouyang, Zhongxue Gan

Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose \textbf{Group Cognition Learning (GCL)}, a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design.

Deep Learning · Foundation Models

Wenzhuo Zhao, Ronghao Xian, Keren Fu, Qijun Zhao

Existing human attention modeling methods persist as highly fragmented across modalities, scenes, and task formulations. Consequently, even with increasing model capacity and data scale, current models predominantly remain scene-dependent and task-specific, failing to practically generalize in real-world applications. To address the fundamental limitations, we present the Attend to Anything Model (AAM), a multi-modal foundation model that unifies attention modeling across various image, video, and audio-visual tasks and scenes. AAM reformulates attention as an asymmetric entailment relationship organized in a general-to-specific hierarchy, implemented through language prompts with hierarchical embeddings in hyperbolic space. Furthermore, to unify static image and dynamic video attention, we adopt a fluid-dynamics perspective, formulating video-frame attention as a diffusive temporal evolution governed by the Fokker--Planck equation. Extensive experiments on 16 benchmarks demonstrate that AAM consistently outperforms state-of-the-art methods by an average of 6\% across various scenarios, while achieving approximately a 4$\times$ speedup in video inference. Overall, these results demonstrate that AAM provides a principled foundation for future research on attention and saliency-related tasks.

Deep Learning · Large Language Models

Qijun Miao, Zhixuan Fang

The rapid advancement of large language models (LLMs) has led to remarkable performance across diverse domains, making them indispensable assistants in daily life and work. Currently, LLM services are primarily accessed in two ways: (i) paid access to cloud-hosted LLMs, which are powerful but introduce nontrivial cost; and (ii) deployment of small language models (SLMs) on personal devices or small clusters, which, while less powerful, are sufficient for handling relatively simple tasks. To achieve a balanced trade-off between monetary cost and task performance, we propose Selective Deferred Routing, a paradigm that enables cost-efficient collaboration between local SLMs and remote LLMs. In this framework, a user request is first processed by the local SLM, which not only generates a preliminary response but also provides rich semantic representations of the request. A lightweight decision module then leverages this information to either adopt the initial response or route the request to the most suitable remote LLM for a higher-quality response. Extensive experiments across diverse model architectures and families, including both SLMs and LLMs, as well as datasets spanning multiple task scenarios, demonstrate that our approach consistently outperforms existing multi-LLM collaboration methods under a wide range of cost–performance trade-offs.

Deep Learning · Generative Models and Autoencoders

Guanghan Wang, Gilad Turok, Yair Schiff, Marianne Arriola, Volodymyr Kuleshov

While diffusion language models (DLMs) have achieved competitive performance in text generation, improving their reasoning ability with reinforcement learning remains an active research area. Here, we introduce d2, a reasoning framework tailored for masked DLMs. Central to our framework is a new policy gradient algorithm that relies on accurate estimates of the sampling trajectory likelihoods. Our likelihood estimator, d2-AnyOrder, achieves exact trajectory likelihood with a single model pass for DLMs that support a sampling algorithm called any-order decoding. Through an empirical study of widely used DLMs, we show that any-order decoding is not universally supported in practice. Consequently, for DLMs that do not naturally support any-order decoding, we propose another estimator, d2-StepMerge, which, unlike d2-AnyOrder, only approximates the trajectory likelihood. d2-StepMerge trades off compute for approximation accuracy in an analytically tractable manner. Empirically, d2 significantly outperforms widely-used RL baselines when applied to popular DLMs, and sets a new state-of-the-art performance for DLMs on logical reasoning tasks (Countdown and Sudoku) and math reasoning benchmarks (GSM8K and MATH500).

Applications · Time Series

Qingwen Zeng, Dajun Guo, Zhaoge Bi, lining chen, Jushang Qiu, Yitian Yang, Carl Yang, Huaming Chen, Ling Chen

Time series forecasting is critical in domains such as finance, energy, and healthcare, yet real-world datasets often exhibit non-stationarity, noise, missing values, and distribution shifts, posing severe challenges for generalization. In practice, industry solutions typically rely on customized forecasting frameworks that combine imputation, decomposition, and specialized models. However, such frameworks are costly to engineer and maintain. Moreover, we observe that many frameworks suffer from the impacts of distribution shifts, which degrade their respective performance. It motivates a paradigm that transfers reliably across heterogeneous datasets while accumulating reusable strategy knowledge for large-scale, dynamic environments. Although large language model-based agents have recently shown strong reasoning and tool-use capabilities, existing approaches do not consistently adapt forecasting workflows across diverse time series. We identify two primary factors, including limited strategy-level supervision and the inherent complexity of mapping dataset-specific meta-features to effective forecasting strategies. To address these challenges, we propose BECRA, a novel agent training paradigm that learns forecasting intelligence through contrast-aware exploration and agent-level causal lesson extraction, without human-annotated supervision. BECRA distills symbolic strategy lessons that support in-context planning on unseen datasets, enabling zero-shot training adaptation.

Social Aspects · Safety

Yuanwei Hu, Bo Peng, Yadan Luo, Jie Lu, Ling Chen, zhen fang

Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision–language models (VLMs) has enabled zero-shot OOD detection without access to in-distribution (ID) training data; in this setting, existing methods commonly treat text embeddings of class names as class prototypes. In this paper, we challenge this widely adopted “text-as-prototype” paradigm by theoretically showing that off-the-shelf textual prototypes are generally misaligned with the optimal visual prototypes, yielding an intrinsic \textit{modality gap} that cannot be eliminated by prompt engineering alone. To mitigate this gap under the post-hoc constraint, this paper presents an online pseudo-supervised framework that directly learns class prototypes in the visual feature space using unlabeled test-time data streams and soft predictions from the pre-trained VLMs. We provide theoretical guarantees for the convergence of the online optimization procedure. Extensive experiments empirically manifest that our method achieves a new state of the art across a variety of OOD detection setups.

Applications · Computer Vision

Christopher Choy, Junha Lee, Chunghyun Park, Minsu Cho, Jan Kautz

Open-vocabulary 3D segmentation is crucial for real-world applications, yet existing methods are constrained by fragmented masks and inconsistent captions in dataset generation, and by multi-stage pipelines prone to error propagation. We present SpaCeFormer-3M, the largest open-vocabulary 3D instance segmentation dataset with 846K instances from 15K scenes, and SpaCeFormer (Space-Curve Transformer), a proposal-free segmentation architecture. Our data pipeline leverages multi-view mask clustering to produce geometry-consistent 3D instances and employs multi-view VLM prompting for view-consistent captions. On the modeling side, SpaCeFormer combines spatial window attention with Morton curve serialization for spatially coherent features, and a RoPE-enhanced decoder to predict instance masks directly from learned queries without external proposals. On ScanNet200, our approach achieves 11.1 zero-shot mAP, a 2.8$\times$ improvement over prior proposal-free methods while requiring only 0.21 seconds per scene.

Deep Learning · Self-Supervised Learning

Yi Liu, Hongji Zhang, Yiwen Wang, Dimitrios Tsaras, Lei Chen, Mingxuan Yuan, Qiang Xu

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.

Deep Learning · Graph Neural Networks

Yoonhyuk Choi, Jiho Choi, Jiwoo Kang

Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a \textbf{G}auge-\textbf{E}quivariant Graph Network with \textbf{S}elf-Interference \textbf{C}ancellation (GESC), which replaces additive aggregation with a projection-based interference mechanism. Unlike prior magnetic or gauge-equivariant GNNs that rely on additive message mixing, GESC explicitly models self-interference arising from redundant low-frequency components. We show that the absence of interference handling in existing gauge-based GNNs is a primary driver of oversmoothing under gauge transport. We introduce a $\mathrm{U}(1)$ phase connection followed by a rank-1 projection that suppresses self-parallel components before attention, and a sign-aware gate that regulates negatively aligned neighbors. Across diverse graph benchmarks, GESC consistently outperforms recent state-of-the-art models while offering a unified, interference-aware view of message passing. Our code is available at \href{https://anonymous.4open.science/r/GESC-1B22}{this link}.

Deep Learning · Large Language Models

Xingyuan Hua, Sheng Yue, Ju Ren

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies, lacking the ability to adaptively distinguish when exploration is truly required. In this paper, we propose an exploration-aware reinforcement learning framework that enables LLM agents to adaptively explore only when uncertainty is high. Our method introduces a fine-grained reward function via variational inference that explicitly evaluates exploratory actions by estimating their potential to improve future decision-making, together with an exploration-aware grouping mechanism that separates exploratory actions from task-completion actions during optimization. By targeting informational gaps, this design allows agents to explore selectively and transition to execution as soon as the task context is clear. Empirically, we demonstrate that our approach achieves consistent improvements across a range of challenging text-based and GUI-based agent benchmarks.

Junxuan Wang, Xuyang Ge, Wentao Shu, Zhengfu He, Xipeng Qiu

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}.

General Machine Learning · Evaluation

Chuhan Li, Rilyn Han, Joy Hsu, Yongyuan Liang, Rajiv Dhawan, Jiajun Wu, Ming-Hsuan Yang, Xin (Eric) Wang

A core aspect of human perception is *situated awareness*, the ability to relate ourselves to the surrounding physical environment and reason over possible actions in context. However, most existing benchmarks for multimodal foundation models (MFMs) emphasize **environment-centric** spatial relations (relations among objects in a scene), while largely overlooking **observer-centric** relationships that require reasoning relative to agent's viewpoint, pose, and motion. To bridge this gap, we introduce SAW-Bench (**S**ituated **A**wareness in the Real **W**orld), a novel benchmark for evaluating egocentric situated awareness using real-world videos. SAW-Bench comprises 786 self-recorded videos captured with Ray-Ban Meta (Gen 2) smart glasses spanning diverse indoor and outdoor environments, and over 2071 *human-annotated* question-answer pairs. It probes a model’s observer–environment understanding with *six* different awareness tasks. Our comprehensive evaluation reveals a human-model performance gap of 31.97%, even with the best-performing MFM, Gemini 3 Flash. Beyond this gap, our in-depth analysis uncovers several notable findings; for example, while models can exploit partial geometric cues in egocentric videos, they often fail to infer a coherent camera geometry, leading to systematic spatial reasoning errors. We position SAW-Bench as a benchmark for situated spatial intelligence, moving beyond passive observation to understanding physically grounded, observer-centric dynamics.

Applications · Everything Else

Bo Yuan, Zelin Zhao, Petr Molodyk, Bin Hu, Yongxin Chen

Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. However, existing fine-tuned models tend to reactively follow the user’s instructions and hallucinate dimensions when the text is ambiguous. To address this, we propose a proactive agentic framework for text-to-CadQuery generation, named as \textbf{ProCAD}, that resolves specification issues before code synthesis. Our framework pairs a proactive clarifying agent, which audits the prompt and asks targeted clarification questions only when necessary to produce a self-consistent specification, with a CAD coding agent that translates the specification into an executable CadQuery program. We fine-tune the coding agent based on a curated high-quality text-to-CadQuery dataset and train the clarifying agent via agentic SFT on clarification trajectories. Experiments show that proactive clarification significantly improves robustness to ambiguous prompts while keeping interaction overhead low. ProCAD outperforms frontier closed-source models, including Claude Sonnet 4.5, reducing the mean Chamfer distance by 79.9\% and lowering the invalidity ratio from 4.8\% to 0.9\%. Our code and datasets will be made publicly available.

Applications · Energy

Katherine Lambert, Sasha Luccioni

The rise in deployment of large language models has driven a surge in GPU demand and datacenter scaling, raising concerns about electricity use, grid stress, and the impacts of modern AI workloads. Distillation is often promoted as one of the most effective paths to obtain cheaper, more efficient models, yet these claims rarely account for the full end-to-end energy and resource costs, including crucial teacher-side workloads such as data generation, logit caching, and evaluation. We present a comprehensive energy accounting framework that measures the complete computational cost of distillation pipelines via detailed stage-wise tracking of GPU device power consumption. In our experiments, we separate and log empirical energy use across distinct phases and systematically measure the energy and emissions of two common distillation methods: the classic logit-based knowledge distillation and synthetic-data supervised fine-tuning, constructing energy–quality–throughput Pareto frontiers that expose the previously ignored costs. From these measurements and analyses, we derive practical design rules for selecting distillation methods and hyperparameters under energy and budget constraints, and release an open-source measurement harness and accounting protocol to provide a standardized foundation for comparable, reproducible distillation research, explicitly accountable for complete pipeline energy impact.

Deep Learning · Large Language Models

Rana Khan, Zijie Liu, Zhen Tan, Charles Fleming, Tianlong Chen

Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on downstream tasks. While RL generally preserves broader model capabilities (retention) better than SFT, it comes with significant costs: complex reward engineering, instability, and expensive on-policy sampling. In contrast, SFT is efficient but brittle, often suffering from catastrophic forgetting due to $\textbf{Supervision Mismatch}$: the divergence between the model's evolving policy and static training labels. We address this trade-off with $\textbf{Trajectory-Mixed Supervision (TMS)}$, a reward-free framework that approximates the on-policy benefits of RL by creating a dynamic curriculum from the model's own historical checkpoints. TMS minimizes $\textit{Policy-Label Divergence (PLD)}$, preventing the mode collapse that drives forgetting in standard SFT. Experiments across reasoning (MATH, GSM8K) and instruction-following benchmarks demonstrate that TMS effectively shifts the accuracy-retention Pareto frontier. While RL remains the gold standard for retention, TMS significantly outperforms standard and iterative SFT, bridging the gap to RL without requiring reward models or verifiers. Mechanistic analysis confirms that PLD drift accurately predicts forgetting, and that TMS successfully mitigates this drift.

Deep Learning · Large Language Models

Isha Puri, Mehul Damani, Idan Shenfeld, Marzyeh Ghassemi, Jacob Andreas, Yoon Kim

Large language models (LMs) are typically post-trained via RL to produce a single best answer per query, implicitly optimizing for modal correctness. While effective for benchmark accuracy, this approach is unideal for many applications of interest such as in medical diagnosis, which would benefit from models generating a set of plausible answers (ideally paired with uncertainty estimates).This paper describes a multi-answer reinforcement learning (RL) approach for enabling LMs to do this, where we modify the RL objective to train models to explicitly generate multiple candidate answers in a single forward pass, internalizing aspects of inference-time search into the model’s generative process. We instantiate this approach through Multi-Answer Reinforcement Learning with Verifiable Rewards (Multi-RLVR), which generalizes ordinary RLVR to the multi-answer case with a set-level reward. We further extend this approach to Multi-Answer Reinforcement Learning with Calibrated Rewards (Multi-RLCR) which adds a set-level Brier score-based calibration objective to enable LMs to output calibrated uncertainty estimates associated with each answer in the output set. Multi-answer training promotes explicit representation of alternative hypotheses rather than repeated generation of the dominant mode. Across question-answering and medical diagnostic benchmarks, we observe improved diversity, recall, and set-level calibration scores compared to single answer-trained baselines. We further observe that models trained with our approach are more token-efficient, requiring fewer tokens to generate multiple answers than competing approaches. These results position multi-answer RL as a principled and compute-efficient alternative to inference-time scaling.