论文检索

General Machine Learning · Transfer, Multitask and Meta-learning

Jiajun Lai, Qi Liu, Shijie Li, Huaiguang Jiang

Continual learning requires models to mitigate catastrophic forgetting of prior knowledge while learning a sequence of tasks. Although existing methods based on orthogonal projection prevent interference by constraining parameter updates, they tend to limit plasticity as the task sequence progresses. The reliance on linear approximation further causes the projected gradients to deviate from the nonlinear manifold. To address these issues, we propose Metabolic Optimization for Continual Learning (MoCL), a rehearsal-free framework that strikes a balance between stability and plasticity. To capture the geometric manifold of prior knowledge, MoCL introduces a factorized subspace approximation that avoids expensive explicit matrix inversion. Given the heavy-tailed distribution of the Fisher Information Matrix, we employ a metabolic gating based on Tsallis entropy to suppress updates that conflict with historical knowledge. Theoretical and empirical analyses reveal that MoCL enables the model to converge to a shared low-loss region across sequential tasks. Extensive experimental results across multiple benchmarks demonstrate that MoCL outperforms state-of-the-art methods in both classification performance and efficiency.

Social Aspects · Safety

Dadi Guo, Qingyu Liu, Dongrui Liu, Qihan Ren, Shuai Shao, Tianyi Qiu, Haoran Li, Yi Fung, Zhongjie Ba, Juntao Dai 等

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment. We observe and define \textit{\textbf{agentic upward deception}}, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting. To assess its prevalence, we construct a benchmark of 200 tasks covering five task types and eight realistic scenarios in a constrained environment, such as broken tools or mismatched information sources. Evaluations of 11 popular LLMs reveal that these agents typically exhibit action-based deceptive behaviors, such as guessing results, performing unsupported simulations, substituting unavailable information sources, and fabricating local files. We further test prompt-based mitigation and find only limited reductions, suggesting that it is difficult to eliminate and highlighting the need for stronger mitigation strategies to ensure the safety of LLM-based agents. The code and data are included in the supplementary materials.

General Machine Learning · Scalable Algorithms

Peyman Afshani, Rezaul Chowdhury, Mayank Goswami, Jens Kristian R Schou, Francesco Silvestri, Mariafiore Tognon

It is known that RandomShuffle, the without replacement version of Stochastic Gradient Descend (SGD), converges faster than with-replacement SGD. However, RandomShuffle requires to uniformly perform a random permutation of the input sequence, which is known to have an high I/O complexity due to data movements over the memory hierarchy. In this paper, we propose a shuffling algorithm with a linear I/O complexity that generates almost-uniformly random permutations with rigorous mathematical guarantees. Specifically, we show that the shuffling algorithm can generate $2$-wise independent permutations. Furthermore, we can extend to $k$-wise independency with a small error in the probability distribution, if the fast memory has at least $k$ memory blocks. These results allow us to reach the same expected theoretical convergence as RandomShuffle while achieving optimal linear I/O cost.

Deep Learning · Large Language Models

Bowei He, Minda Hu, Zenan Xu, Hongru WANG, Licheng Zong, Yankai Chen, Chen Ma, Xue Liu, PlutoZhou, Irwin King

Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement learning is hindered by the *multi-scale credit assignment* problem: existing methods typically rely on sparse, trajectory-level rewards that fail to distinguish between high-quality reasoning and fortuitous guesses, leading to redundant or misleading search behaviors. To address this, we propose Search-R2, a novel Actor–Refiner collaboration framework that enhances reasoning through targeted intervention, with both components jointly optimized during training. Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories, and a Meta-Refiner, which selectively diagnoses and repairs flawed steps via a ``cut-and-regenerate'' mechanism. To provide fine-grained supervision, we introduce a hybrid reward design that couples outcome correctness with a dense process reward quantifying the information density of retrieved evidence. Theoretically, we formalize the Actor–Refiner interaction as a smoothed mixture policy, proving that selective correction yields strict performance gains over strong baselines. Extensive experiments across various general and multi-hop QA datasets demonstrate that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales, achieving superior reasoning accuracy with minimal overhead.

General Machine Learning · Scalable Algorithms

DaeHun Nyang

Cosine similarity estimation is a core primitive in coarse-to-fine retrieval pipelines, where early-stage candidate selection relies on approximate similarity estimates whose errors are amplified downstream. Widely used sign-based sketches arising from extreme quantization of random projections exhibit a structural variance peak near $\theta$ $\approx$ 90$^\circ$, the near-background region where candidate selection is most difficult. We propose QA-Cos, a query-aware decoder-side estimator that departs from the Hamming-agreement paradigm, treating sign bits as probabilistic observations rather than deterministic votes. Across simulations and BEIR benchmarks, QA-Cos reduces estimation error by up to $\sim$15--20\% in the near-orthogonal region and translates these gains into improved candidate selection in two-stage ANN pipelines, improving Hit@K by up to $\sim$30 percentage points at fixed budgets and reducing candidates by up to $\sim$45--50\% at fixed recall.

Deep Learning · Generative Models and Autoencoders

Yunhan Yang, Chunshi Wang, Junliang Ye, YANG LI, Zanxin Chen, Zehuan Huang, Yao Mu, Zhuo Chen, Chunchao Guo, Xihui Liu

Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in functional logic and hierarchical physics. To bridge this gap, we introduce PhysForge, a decoupled two-stage framework supported by PhysDB, a large-scale dataset of 150,000 assets with four-tier physical annotations. First, a VLM acts as a physical architect to plan a Hierarchical Physical Blueprint defining material, functional, and kinematic constraints. Second, a physics-grounded diffusion model realizes this blueprint by synthesizing high-fidelity geometry alongside precise kinematic parameters via a novel KineVoxel Injection (KVI) mechanism. Experiments demonstrate that PhysForge produces functionally plausible, simulation-ready assets, providing a robust data engine for interactive 3D content and embodied agents.

General Machine Learning · Scalable Algorithms

Haoran Zhang, Dongjun Kim, Seohyeon Cha, Haris Vikalo

Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data. In practice, however, a discrepancy between the factor-wise averaging used to preserve low rank and the mathematically correct aggregation of local updates can cause significant aggregation error and unstable training. We argue that a major source of this problem is *rotational misalignment*, arising from the rotational invariance of low-rank factorizations -- semantically equivalent updates can be represented in different latent subspaces across clients since $(B_i R_i)(R_i^\top A_i) = B_i A_i$. When such misaligned factors are averaged directly, they interfere destructively and degrade the global update. To address this issue, we propose **FedRot-LoRA**, a federated LoRA framework that aligns client updates via orthogonal transformations prior to aggregation. This alignment preserves the semantic update while reducing cross-client subspace mismatch, without increasing communication cost or restricting model expressivity. We provide a convergence analysis that examines the aggregation error induced by factor-wise averaging and shows how rotational alignment yields a tighter upper bound on this error. Extensive experiments on natural language understanding and generative tasks demonstrate that FedRot-LoRA consistently outperforms existing federated LoRA baselines across a range of heterogeneity levels and LoRA ranks. Code is available at https://anonymous.4open.science/r/FedRot-LoRA

Optimization · Stochastic

Egor Gladin, Alexey Kroshnin, Jia-Jie Zhu, Pavel Dvurechenskii

The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In practice, when the number of exponential terms inside the logarithm is large or infinite, optimization becomes challenging since computing the gradient requires differentiating every term. We propose a novel convexity- and smoothness-preserving approximation to LogSumExp that can be efficiently optimized using stochastic gradient methods. This approximation is rooted in a sound modification of the KL divergence in the dual, resulting in a new $f$-divergence called the *safe KL divergence*. Our experiments and theoretical analysis of the LogSumExp-based stochastic optimization, arising in DRO and continuous OT, demonstrate the advantages of our approach over existing baselines.

General Machine Learning · Scalable Algorithms

Elias Jääsaari, Ville Hyvönen, Teemu Roos

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both queries and documents are encoded using one embedding for each token, and similarity between queries and documents is measured by the MaxSim similarity measure. However, the improved recall of multi-vector retrieval comes at the expense of significantly increased latency. This necessitates designing efficient approximate nearest neighbor search (ANNS) algorithms for multi-vector search. In this work, we introduce LEMUR, a simple-yet-efficient framework for multi-vector similarity search. LEMUR consists of two consecutive problem reductions: We first formulate multi-vector similarity search as a supervised learning problem that can be solved using a one-hidden-layer neural network. Second, we reduce inference under this model to single-vector similarity search in its latent space, which enables the use of existing single-vector ANNS methods for speeding up retrieval. In addition to performance evaluation on ColBERTv2 embeddings, we evaluate LEMUR on embeddings generated by modern multi-vector text models and multi-vector visual document retrieval models. LEMUR is an order of magnitude faster than earlier multi-vector similarity search methods.

Theory · Optimization

Zusen Xu, Jia-Jie Zhu

We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Monte Carlo sampling and statistical optimal transport, we show that our theoretical framework can be implemented as practical algorithms for sampling from worst-case distributions and, consequently, DRO. While numerous previous works have relied on dual reformulation techniques, we contribute a sound and complete gradient flow view based on SDEs or PDEs that can be used to construct new algorithms for general, potentially non-convex, losses. Without loss of generality, we solve a class of Wasserstein and entropy-regularized DRO problems using the recently-discovered Wasserstein Fisher-Rao and Stein variational gradient flows. Notably, we also show some simple reductions of our framework recover exactly previously proposed popular DRO methods, and provide new insights into their theoretical limits and optimization dynamics of DRO. Numerical studies based on stochastic gradient descent on machine learning tasks provide empirical backing for our theoretical findings.

Deep Learning · Generative Models and Autoencoders

Samuel Garcin, Tom Walker, Steven McDonagh, Tim Pearce, Hakan Bilen, Tianyu He, Kaixin Wang, Jiang Bian

Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must be implicitly learned from data, and spatial memory is restricted to limited temporal context windows. This results in an unrealistic user experience, and presents significant obstacles to down-stream tasks such as training agents. To address this, we present PERSIST, a new paradigm of world model which simulates the evolution of a latent 3D scene: environment, camera and renderer. This allows us to synthesize new frames with persistent spatial memory and consistent geometry. Our approach achieves substantial improvements in spatial memory, 3D consistency, and long-horizon video generation quality over existing methods, producing coherent and evolving 3D worlds.

General Machine Learning · Representation Learning

Luyao Tang, Jiewei Zheng, Kunze Huang, Chaoqi Chen, Yue Huang, Cheng Chen

Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositional reasoning: reusing primitives learned from known classes and deciding when new combinations imply new categories. Existing GCD methods operate on unstructured token features and struggle to extrapolate to novel compositions. We propose CoGe-GCD, which rethinks GCD through compositional generalization with two coupled stages. (i) Compositional Perception structures patch tokens by mapping them to a small vocabulary of primitives and refining token embeddings via competitive token-primitive assignment and information passing, yielding coherent groups for discovery. (ii) Generalizing Induction exploits the induced geometric structure and applies a geometric-structure-preserving calibration over spatial relations, maintaining probabilistic semantics while improving extrapolation to unseen primitive combinations. CoGe-GCD is implemented as an inductive-bias module between backbone and projection head, without modifying heads or losses, and can be plugged into diverse GCD frameworks. On standard benchmarks, it consistently improves all-class accuracy, unknown-class number estimation, and geometric quality, with marginal computational overhead.

General Machine Learning · Kernel methods

Alejandro de la Concha Duarte, Nicolas Vayatis, Argyris Kalogeratos

This paper introduces the Collaborative Likelihood-ratio Estimation problem, which is relevant for applications involving multiple statistical estimation tasks that can be mapped to the nodes of a fixed graph expressing pairwise task similarity. Each graph node $v$ observes i.i.d data from two unknown node-specific pdfs, $p_{v}$ and $q_{v}$, and the goal is to estimate the likelihood-ratios (or density-ratios), $r_{v}(x)=\frac{q_{v}(x)}{p_{v}(x)}$, for all $v$. Our contribution is multifold: we present a non-parametric collaborative framework that leverages the graph structure of the problem to solve the tasks more efficiently; we present a concrete method that we call Graph-based Relative Unconstrained Least-Squares Importance Fitting (GRULSIF) along with an efficient implementation; we derive convergence rates that highlight the role of the main variables of the problem. Our theoretical results explicit the conditions under which the collaborative estimation leads to performance gains compared to solving each estimation task independently. Finally, in a series of experiments, we demonstrate that the joint likelihood-ratio estimation of GRULSIF at all graph nodes is more accurate compared to state-of-the-art methods that operate independently at each node, and we verify that the behavior of GRULSIF is in agreement with our theoretical analysis.

General Machine Learning · Evaluation

Weijia Li, KE GAO, Jiajie Li, Han Sun, Yuhe Ding, Yongdong Mai, Yiran Le, Yongjie Qian, Zhibin Zhang, Xinyu Wang 等

Cross-architecture migration of high-performance libraries dictates ecosystem readiness on emerging hardware. The challenge is twofold: disentangling library-scale dependencies and performance-critical kernels with ISA-specific SIMD intrinsics, often trading migration speed for peak performance. While LLM-based agents offer a promising approach, are confined to function-level tasks or scalar code, failing to assess agents’ capabilities and limitations in realistic, library-scale migration. We present CLAM-Bench (Cross-architecture Library-scale Agent Migration benchmark), featuring 85 critical kernels from widely used libraries, including OpenCV, libjpeg, and NCNN. It supports comprehensive evaluations of compilability, correctness, and performance across major transitions: ARM→RISC-V, x86→ARM, and ARM→LoongArch. Evaluation of 12 SOTA agent-LLM combinations on CLAM-Bench reveals that, due to the lack of library-level navigation and hardware-aware optimization, agents regress to superficial pattern matching, yielding only 20.88% correctness and 0.83x speedup for libjpeg. Motivated by these findings, we further propose FSCM, a multi-agent framework incorporating hardware-aware global reconfiguration and performance optimization. FSCM improves OpenCV correctness to 71%. The benchmark and code are available at https://anonymous.4open.science/r/clam_bench-D8EB/.

Deep Learning · Generative Models and Autoencoders

Yufan Deng, Zilin Pan, Hongyu Zhang, Xiaojie Li, Huruoqing, Yufei Ding, Yiming Zou, Yan Zeng, Zhou Daquan

While video generation holds promise for embodied intelligence, current video models struggle with physical realism, and progress is hindered by the lack of standardized benchmarks. To address this gap, we introduce a comprehensive robotics benchmark, RBench, designed to evaluate robot-oriented video generation across five task domains and four distinct embodiments. By assessing task correctness and visual fidelity through reproducible metrics, our evaluation of 25 models reveals significant deficiencies in generating physically realistic robot behaviors. Furthermore, the benchmark achieves a 0.96 Spearman correlation with human judgment, validating its effectiveness. While RBench provides the necessary lens to identify these deficiencies, achieving physical realism requires moving beyond evaluation to address the critical shortage of high-quality training data. Driven by these insights, we introduce a refined four-stage data pipeline, resulting in RoVid-X, the largest open-source robotic dataset for video generation with 4 million annotated video clips, covering thousands of tasks and enriched with physical property annotations. Extensive experiments demonstrate that finetuning on RoVid-X yields consistent performance gains. Collectively, this synergistic ecosystem of evaluation and data establishes a robust foundation for rigorous assessment and scalable training of video models, accelerating the evolution of embodied AI toward physical intelligence. The code and video demos are available in the supplementary materials.

General Machine Learning · Evaluation

Jinyeop Song, Jeff Gore, Max Kleiman-Weiner

As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation frameworks beyond costly, manually-designed benchmarks. We propose information-theoretic evaluation based on empowerment, an information-theoretic measure of an agent's influence on future states through its actions. To handle the unique challenges of text-based environments, we introduce EELMA (Estimating Empowerment of Language Model Agents), an algorithm for approximating effective empowerment from multi-turn text interactions. We demonstrate EELMA on textual games and web-browsing scenarios, showing that empowerment strongly correlates with average task performance. We further analyze how empowerment varies across models, environment complexity, and agent configurations, and show that high-empowerment states and actions often mark pivotal moments for general capabilities. These results establish empowerment as a general-purpose metric for evaluating LM agents in open-ended settings. Code available: https://anonymous.4open.science/r/EELMA-E227

Applications · Computer Vision

Qingdong He, Xueqin Chen, Chaoyi Wang, Yanjie Pan, Xiaobin Hu, Zhenye Gan, Chengjie Wang, Xiangtai Li, Jiangning Zhang, Yabiao Wang

Instruction-based image editing (IIE) has advanced rapidly with the success of diffusion models. However, existing efforts primarily focus on simple and explicit instructions to execute editing operations such as adding, deleting, moving, or swapping objects. They struggle to handle more complex implicit hypothetical instructions that require deeper reasoning to infer plausible visual changes and user intent. Additionally, current datasets provide limited support for training and evaluating reasoning-aware editing capabilities. Architecturally, these methods also lack mechanisms for fine-grained detail extraction that support such reasoning. To address these limitations, we propose Reason50K, a large-scale dataset specifically curated for training and evaluating hypothetical instruction–reasoning image editing, along with ReasonBrain, a novel framework designed to reason over and execute implicit hypothetical instructions across diverse scenarios. Reason50K includes over 50K samples spanning four key reasoning scenarios: Physical, Temporal, Causal, and Story reasoning. ReasonBrain leverages Multimodal Large Language Models (MLLMs) for editing guidance generation and a diffusion model for image synthesis, incorporating a Fine-grained Reasoning Cue Extraction (FRCE) module to capture detailed visual and textual semantics essential for supporting instruction reasoning. To mitigate the semantic loss, we further introduce a Cross-Modal Enhancer (CME) that enables rich interactions between the fine-grained cues and MLLM-derived features. Extensive experiments demonstrate that ReasonBrain consistently outperforms state-of-the-art baselines on reasoning scenarios while exhibiting strong zero-shot generalization to conventional IIE tasks. Our dataset and code will be released publicly.

Deep Learning · Generative Models and Autoencoders

Marcel Hirt, Domenico Campolo, Victoria Leong, Juan-Pablo Ortega

Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. Multi-modal Variational Autoencoders (VAEs) have been a popular generative model class that learns latent representations that jointly explain multiple modalities. Various objective functions for such models have been suggested, often motivated as lower bounds on the multi-modal data log-likelihood or from information-theoretic considerations. To encode latent variables from different modality subsets, Product-of-Experts (PoE) or Mixture-of-Experts (MoE) aggregation schemes have been routinely used and shown to yield different trade-offs, for instance, regarding their generative quality or consistency across multiple modalities. In this work, we consider a variational objective that can tightly approximate the data log-likelihood. We develop more flexible aggregation schemes that avoid the inductive biases in PoE or MoE approaches by combining encoded features from different modalities based on permutation-invariant neural networks. Our numerical experiments illustrate trade-offs for multi-modal variational objectives and various aggregation schemes. We show that our variational objective and more flexible aggregation models can become beneficial when one wants to approximate the true joint distribution over observed modalities and latent variables in identifiable models.

Social Aspects · Safety

Rico Angell, Raghav Singhal, Zachary Horvitz, Zhou Yu, Rajesh Ranganath, Kathleen McKeown, He He

Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significantly reduced the likelihood of harmful model outputs. However, when models are queried billions of times in a day, even rare worst-case behaviors will occur. Current safety evaluations focus on capturing the distribution of inputs that yield harmful outputs. These evaluations disregard the probabilistic nature of models and their tail output behavior. To measure this tail risk, we propose a method to efficiently estimate the probability of harmful outputs for any input query. Instead of naive brute-force sampling from the target model, where harmful outputs could be rare, we operationalize importance sampling by creating unsafe versions of the target model. These unsafe versions enable sample-efficient estimation by making harmful outputs more probable. On benchmarks measuring misuse and misalignment, these estimates match brute-force Monte Carlo estimates using 10–20× fewer samples. For example, we can estimate probability of harmful outputs on the order of $10^{−4}$ with just 500 samples. Additionally, we find that these harmfulness estimates can reveal the sensitivity of models to perturbations in model input and predict deployment risks. Our work demonstrates that rare-event estimation is both critical and feasible for safety evaluations.

Applications · Computer Vision

Shawn Leung, Jiacheng Liu, Mingyang Sun, Qichen He, Anda Cheng, Cewu Lu, Jianhua Sun

Real-world physical sensing exhibits complex, heterogeneous noise patterns that deviate significantly from idealized simulation, posing a fundamental bottleneck for sim-to-real transfer. Existing sensor modelings typically treat depth noise as a monolithic black-box process, overlooking the distinct physical mechanisms that govern different error modalities. In this work, we introduce a physics-grounded paradigm that disentangles monolithic noise into two complementary modalities: sensing invalidation and measurement inaccuracy, enabling a tailored treatment of noise sources based on their physical origins. Building on this insight, we propose PRISM (Physics-Reasoned Implicit Sensor Modeling), a tripartite framework that distills 3D Visual Foundation Model features as rich spatial-semantic priors for physics-based reasoning. To address the inherent sparsity and class imbalance of invalidation regions, we develop Hierarchical Positive-Prioritized Supervision, integrating multi-scale positive-weighted objectives with a positive-preserving dynamic hard mining strategy to enforce precise artifact delineation. Extensive benchmarks demonstrate that PRISM achieves state-of-the-art fidelity in noisy depth synthesis. Furthermore, downstream robotic experiments show that PRISM facilitates a 93.8\% average success rate in the real world, marking a significant improvement over monolithic baselines.