论文检索

Applications · Robotics

Qian He, Zhenshuo Yang, Wenqi Liang, Chunhui Hao, Nicu Sebe, Jiandong Tian

Visuomotor policies aim to learn complex manipulation tasks from expert demonstrations. However, generating smooth and coherent trajectories remains challenging, as it requires balancing proximal precision with distal foresight. Existing approaches typically focus on optimizing intra-chunk action distributions, often neglecting the inter-chunk coherence. Consequently, inter-chunk discontinuities significantly impede the learning of coherent long-horizon actions. To overcome this limitation and achieve a synergetic balance between precision and foresight, we propose FocalPolicy, a foresight-aware visuomotor policy that combines Frequency-Optimized Chunking with Locally Anchored flow matching. We introduce a foresight composite objective that supervises time-domain alignment within the proximal actions while regularizing frequency-domain structure over multiple future action chunks to improve cross-chunk coherence. To efficiently learn complex action distributions, we design locally anchored campling to enhance target signal propagation efficiency during consistency flow matching training. Extensive experiments demonstrate that our method consistently outperforms existing approaches while further validating the effective generalizability of our proposed modules to other baseline models. The project will be released as open source.

Applications · Computer Vision

Benno Krojer, Perampalli Shravan Nayak, Oscar Mañas, Vaibhav Adlakha, Desmond Elliott, Siva Reddy, Marius Mosbach

Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP transformation. To understand why LLMs can so readily process visual tokens, we need interpretability methods that reveal what is encoded in the visual token representations at *every* layer of LLM processing. In this work, we introduce LatentLens, a novel approach for mapping latent representations to descriptions in natural language. LatentLens encodes a large text corpus and stores contextualized token representations for each token in that corpus. Visual token representations are then compared to these contextualized representations and the top-$k$ nearest neighbor representations serve as descriptions of the visual token. We evaluate this method on 10 different VLMs, showing that commonly used methods, such as LogitLens, substantially underestimate the interpretability of visual tokens. With LatentLens instead, the majority of visual tokens are interpretable across all studied models and all layers. Qualitatively, we show that the descriptions produced by LatentLens are semantically meaningful and provide more fine-grained interpretations for humans compared to individual tokens. More broadly, our findings contribute new evidence on the alignment between vision and language representations and open up new directions for analyzing the latent representations of LLMs.

Deep Learning · Generative Models and Autoencoders

Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti

We investigate the role of network architecture in shaping the inductive biases of modern score-based generative models. To this end, we introduce the Score Anisotropy Directions (SADs), architecture-dependent directions that reveal how different networks preferentially capture data structure. Our analysis shows that SADs form adaptive bases aligned with the architecture's output geometry, providing a principled way to predict generalization ability in score models prior to training. Through both synthetic data and standard image benchmarks, we demonstrate that SADs reliably capture fine-grained model behavior and correlate with downstream performance, as measured by Wasserstein metrics. Our work offers a new lens for explaining and predicting directional biases of generative models. Code to reproduce our experiments is included in the supplementary material.

Deep Learning · Other Representation Learning

Arip Asadulaev, Rayan Banerjee, Fakhri Karray, Martin Takac

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a network’s depth, allowing it to compactly emulate the capacity of larger models. However, the performance of recursively added layers remains behind the capabilities of one‑pass models with the same feed-forward depth. This means that in the looped version, not every recursive step effectively contributes to depth. This raises the question: when and why does latent reasoning improve performance, and when does it result in dead compute? In our work, we analyze the algorithms that latent reasoning provides answer to this question. We show that latent reasoning can be formalized as a classifier‑free guidance and policy improvement algorithm. Building on these insights, we propose to use a training schemes from RL and diffusion methods for latent reasoning modles. Using the Tiny Recursive Model as our testbed, we show that with our modifications we can avoid dead compute steps and reduce the total number of forward passes by 18× while maintaining performance. Broadly speaking, we show how a policy improvement perspective on recursive steps can explain model behavior and provide insights for further improvements.

Zhimeng Guo, Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Minhao Cheng

As LLMs increasingly generate production code, protecting intellectual property demands watermarking techniques that respect code's strict syntactic constraints. In this work, we introduce CodeTracer, an innovative adaptive code watermarking framework underpinned by a reinforcement learning training paradigm. At its core, CodeTracer features a policy-driven approach that utilizes a parameterized model to intelligently bias token choices during next-token prediction. This strategy ensures that embedded watermarks maintain code functionality while exhibiting subtle yet statistically detectable deviations from typical token distributions. To facilitate policy learning, we devise a comprehensive reward system that seamlessly integrates execution feedback with watermark embedding signals, balancing process-level and outcome-level rewards. To enable gradient-based optimization of these discrete watermarking decisions, we employ Gumbel Top-k reparameterization. Extensive comparative evaluations demonstrate that CodeTracer outperforms state-of-the-art baselines across multiple benchmarks in both watermark detectability and code functionality. Our code is available at https://anonymous.4open.science/r/CodeTracer-B8EE.

Xingwu Chen, Lu Miao, Beining Wu, Difan Zou

Scaling test-time computation during language model inference, such as generating intermediate thoughts or sampling multiple candidate answers, has proven effective in improving model performance. While these techniques inherently rely on the stochastic nature of inference to explore diverse reasoning paths, prior theoretical works typically build on a *deterministic decoding* framework, overlooking the stochastic nature of practical language model inference. This work takes an initial step to bridge this gap by establishing a new theoretical framework, incorporating *randomness and sampling* directly into the decoding analysis. To demonstrate the framework's effectiveness, we apply it to the canonical in-context linear regression task with continuous and binary coefficients, simulating decoding via noise injection and sampling to analyze widely adopted inference techniques. We validate our theoretical findings through numerical simulations, with additional experiments on real-world tasks substantiating the framework's potential for practical applications.

Deep Learning · Large Language Models

Huaisheng Zhu, Zhengyu Chen, Shijie Zhou, Zhihui Xie, Yige Yuan, Shiqi Chen, Zhimeng Guo, Siyuan Xu, Hangfan Zhang, Teng Xiao 等

Recent Uniform-state Diffusion Models (USDMs), initialized from a uniform prior, offer the promise of fast text generation due to their inherent self-correction ability compared to masked diffusion models. However, they still rely on complex loss formulations with additional computational overhead, which hinders scalability. In this work, we explore a simplified denoising-based loss for USDMs that optimizes only noise-replaced tokens, stabilizing training while matching the performance of prior methods with more complex objectives. In addition, we introduce an efficient regularization term to mitigate corruption toward uniform output distributions, which further improves performance. We demonstrate the effectiveness and efficiency of our simple and improved loss formulations by pretraining models on widely used text datasets for USDMs. More importantly, our conclusions scale to larger models, showing strong potential for large-scale training.

General Machine Learning · Scalable Algorithms

Haike Xu, Sandeep Silwal, Piotr Indyk

We propose a new ``bi-metric'' framework for designing nearest neighbor data structures. Our framework assumes two dissimilarity functions: a ground-truth metric that is accurate but expensive to compute, and a proxy metric that is cheaper but less accurate. In both theory and practice, we show how to construct data structures using only the proxy metric such that the query procedure achieves the accuracy of the expensive metric, while only using a limited number of calls to both metrics. Our theoretical results instantiate this framework for two popular nearest neighbor search algorithms: DiskANN and Cover Tree. In both cases we show that, as long as the proxy metric used to construct the data structure approximates the ground-truth metric up to a bounded factor, our data structure achieves arbitrarily good approximation guarantees with respect to the ground-truth metric. On the empirical side, we apply the framework to the text retrieval problem with two dissimilarity functions evaluated by ML models with vastly different computational costs. We observe that for almost all the large data sets in the BEIR benchmark, our approach achieves a considerably better accuracy-efficiency tradeoff than the alternatives, such as retrieve-then-rerank.

Optimization · Large Scale, Parallel and Distributed

Demyan Yarmoshik, Nhat Trung Nguyen, Alexander Rogozin, Alexander Gasnikov

This paper considers decentralized optimization of convex functions with mixed affine equality constraints involving both local and global variables. Constraints on global variables may vary across different nodes in the network, while local variables are subject to coupled and node-specific constraints. Such problem formulations arise in machine learning applications, including federated learning and multi-task learning, as well as in resource allocation and distributed control. We analyze this problem under smooth and non-smooth assumptions, considering both strongly convex and general convex objective functions. Our main contribution is an optimal algorithm for the smooth, strongly convex regime, whose convergence rate matches established lower complexity bounds. We further provide near-optimal methods for the remaining cases.

Reinforcement Learning · Deep RL

Xingyu Jiang, Yuheng Pan, Mukang You, Xiuhui Zhang, Ning Gao, Guanwei Yan, Hao Li, Yue Deng

Model-based reinforcement learning aims to construct world models for efficient sampling. Current mainstream algorithms can be broadly categorized into two paradigms: maximum likelihood and value-aware world models. The former employs structured Recurrent/Transformer State-Space Models to capture environmental dynamics but overlooks task-relevant features. The latter prioritizes decision-critical states but suffers from sub-optimal performance. While recent efforts have sought to integrate these approaches, they typically rely on auxiliary modules or heavy external priors that significantly increase computational complexity. In this work, we propose a Value-Aligned World Model, a minimalist framework designed to synergize these two paradigms with negligible overhead. Specifically, We introduce an intrinsic latent-space value-alignment regularization that compels the world model to prioritize task-relevant features while maintaining the structural integrity of stochastic dynamics. To ensure stable optimization, we develop an adaptive weighting mechanism that acts as a self-regulating curriculum, balancing reconstruction fidelity with decision-making utility. Extensive experiments on Atari 100k and DeepMind Control benchmarks demonstrate that our algorithm consistently boosts existing methods with minimal added code and computational overhead. Code is available at supplementary material.

Deep Learning · Large Language Models

Hang Ding, Dongqi Liu, Qiming Feng, Jian Li, Tong Lei, Jiafu Wu, Shuo Wang, Jiangning Zhang, Chengjie Wang, Yabiao Wang

Reinforcement learning from verifiable rewards (RLVR) has become an important paradigm for enhancing the reasoning capabilities of large language models, while it also involves a persistent tradeoff between optimization stability and learning efficiency. Token-level importance weighting supports fine-grained credit assignment, but it often introduces high variance and unstable parameter updates, whereas sequence-level optimization provides more stable learning dynamics while failing to fully exploit informative local signals. We introduce **T**rust-**G**ated **P**olicy **O**ptimization (TGPO), an efficient policy optimization framework that integrates two complementary mechanisms, namely *sequence anchors* and *information gates*. TGPO aligns token-wise updates with a stable sequence-level reference, which reduces the influence of extreme local likelihood fluctuations on the gradient, and a trust-based information gate adaptively modulates the contribution of token-level signals. By retaining and reweighting gradients from imperfect trajectories rather than excluding them, TGPO improves gradient utilization and sample efficiency while maintaining stable optimization behavior. Empirical results across seven mathematical reasoning datasets and multiple model scales show that TGPO consistently enhances learning efficiency and overall performance in outcome-supervised reinforcement learning settings.

Deep Learning · Large Language Models

Lingyue Fu, Xin Ding, Linyue Pan, Yaoming Zhu, Shao Zhang, Lin Qiu, Weiwen Liu, Weinan Zhang, Xuezhi Cao, Xunliang Cai 等

Current evaluation for Large Language Model (LLM) code agents predominantly focus on generating functional code in single-turn scenarios, which fails to evaluate the agent's capability for continuous code optimization and multi-turn iterative development. To bridge this gap, we introduce CATArena, a framework designed to evaluate the evolutionary capabilities of code agents via iterative tournaments. Agents engage in multi-turn tournaments and continuously refine their code through self-reflection and peer-learning based on comprehensive execution feedback. For evaluation, we propose a dual-metric system to decouple static generation proficiency from evolutionary potential. Extensive experiments reveal that an agent's evolutionary potential is not strictly correlated with its initial proficiency. Our analysis further reveals that current agents struggle to concurrently leverage both peer-learning and self-reflection for effective performance gains. Furthermore, the results validate CATArena's high extensibility and resistance to variance tasks, establishing it as a continuous and reliable standard for assessing the evolutionary capability of LLM code agents.

General Machine Learning · Scalable Algorithms

Zhikai Li, Zhen Dong, Xuewen Liu, Jing Zhang, Qingyi Gu

Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generation tasks. However, their massive parameter scale leads to significant resource consumption and latency during inference. Post-training weight-only quantization offers a promising solution by reducing model size and accelerating token generation through alleviating the memory-bound issue. Nevertheless, there are inherent systematic outliers in weights, and although some efforts have attempted to address them, such as scaling and rotation, the performance of low-bit quantization remains far from satisfactory. In this paper, we propose Outlier Self-Absorption Quantization (OSAQ), which performs second-order low-rank derived additive weight suppression for low-bit weight-only LLM quantization. Specifically, we observe that Hessian exhibits low-rank consistency across different inputs, with certain directions persistently lacking strength. Leveraging this property, we construct an additive weight transformation based on the Hessian’s null space, thereby suppressing weight outliers without affecting the task loss. This additive transformation can be absorbed into the weights offline, requiring no inter-layer transformations and introducing no inference overhead. Moreover, the construction is efficiently achieved by a closed-form solution, without resource-intensive training or iterative procedures. Extensive experiments across models of varying scales and tasks are conducted, and the results show that OSAQ effectively suppresses outliers and improves low-bit quantization performance.

Social Aspects · Fairness

Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis

Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing approaches frequently depend on curated prompt datasets - either manually constructed or generated with large language models (LLMs) - as part of their training and/or evaluation procedures. Beside the curation cost, this also risks overlooking unanticipated, less obvious prompts that trigger biased generation, even in models that have undergone debiasing. In this work, we introduce Bias-Guided Prompt Search (BGPS), a framework that automatically generates prompts that aim to maximize the presence of biases in the resulting images. BGPS comprises two components: (1) an LLM instructed to produce attribute-neutral prompts and (2) attribute classifiers acting on the TTI’s internal representations that steer the decoding process of the LLM toward regions of the prompt space that amplify the image attributes of interest. We conduct extensive experiments on Stable Diffusion 1.5 and a state-of-the-art debiased model and discover an array of subtle and previously undocumented biases that severely deteriorate fairness metrics. Crucially, the discovered prompts are interpretable, i.e they may be entered by a typical user, quantitatively improving the perplexity metric compared to a prominent hard prompt optimization counterpart. Our findings uncover TTI vulnerabilities, while BGPS expands the bias search space and can act as a new evaluation tool for bias mitigation.

Probabilistic Methods · Bayesian Models and Methods

John-Joseph Brady, Nikolas Nüsken, Yunpeng Li

Latent state space systems are ubiquitous in statistical modelling, arising naturally when a time-series is observed through a noisy measurement function, however training deep state space models (DSSM) at scale remains difficult. Two largely distinct strategies and literatures have developed around the training of DSSMs. Firstly, auto-encoding DSSMs train generative DSSMs by optimising a variational lower bound. Secondly, DSSMs trained by back-propagating the outputs of a classical sequential Monte Carlo algorithm (SMC). Such approaches can train DSSMs for discriminative as well as generative tasks, however, due to the sequentiality of their forward pass, scale poorly on modern hardware. We propose a new training method _Parallel Variational Monte Carlo_ (PVMC) that bridges the gap between the paradigms, and can be used robustly to train DSSMs for both discriminative and generative tasks. Our method achieves state-of-the-art or better results on a set of baseline experiments and trains $10\times$ faster than the fastest competing SMC approach.

Social Aspects · Fairness

Jiaee Cheong, Abtin Mogharabin, Paul Pu Liang, Hatice Gunes, Sinan Kalkan

Multimodal Self-Supervised Learning (SSL) has achieved remarkable success by learning representations from multiple views of data. However, prevalent methods rely on the redundancy assumption—that different views share substantial task-relevant information. We argue that this assumption fails in complex, real-world settings characterized by heterogeneity (e.g., variable-length healthcare or behavioral data), where enforcing strict alignment can discard unique, modality-specific signals and inadvertently amplify bias. In this work, we propose FairSSL, a framework that leverages data heterogeneity as a resource for fairness rather than a hindrance. Unlike standard contrastive approaches, FairSSL uses a subject-aware Variance-Invariance-Covariance Regularization objective, where alignment is enforced across segments drawn from the same subject. We introduce a segment-based pooling strategy to handle variable-length modalities, and we regularize representations to encourage (i) sufficient within-subject variability, (ii) cross-modal and cross-subject invariance, and (iii) representation decorrelation. Theoretical analysis shows that our objective bounds the score gap between protected groups. Empirically, FairSSL significantly outperforms existing baselines on heterogeneous multimodal datasets, improving fairness without sacrificing downstream predictive performance.

Deep Learning · Large Language Models

Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Russ Salakhutdinov, Manzil Zaheer, Sanjeev Arora, Anirudh Goyal

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier, e.g., better accuracy with lower context length and/or latency? Abstractly, we view the model as an improvement operator on its own "thoughts" with a continuum of possible strategies. We identify an interesting inference family Parallel-Distill-Refine (PDR), which performs the following: (i) generate diverse drafts in parallel; (ii) distill them into a bounded, textual workspace; and (iii) refine conditioned on this workspace, producing an output that seeds the next round. Importantly, context length (hence compute cost) is controllable via degree of parallelism, and is no longer conflated with the total number of generated tokens. We report PDR instantiations of current models that give better accuracy than long CoT while incurring lower latency. Setting degree of parallelism to 1 yields an interesting subcase, Sequential Refinement (SR) (iteratively improve a single candidate answer) which provides performance superior to long CoT. Success of such model orchestrations raises the question whether further training could shift the Pareto frontier. To this end, we train an 8B thinking model with Reinforcement Learning (RL) to make it consistent with PDR as the inference method. On math tasks with verifiable answers, iterative pipelines surpass single-pass baselines at matched sequential budgets, with PDR delivering the largest gains (e.g., +11% on AIME 2024 and +9% on AIME 2025).

Optimization · Large Scale, Parallel and Distributed

Qiyuan Chen, Xian Wu, Yi Wang, Xianhao Chen

Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimization can significantly reduce memory footprints, it typically suffers from prohibitively degraded convergence speed. To resolve this dilemma, we propose *Hybrid-Order Split Federated Learning* (HO-SFL). By reformulating the split learning process within a Lagrangian framework, HO-SFL decouples the optimization landscape: The server performs precise first-order updates (i.e., BP), whereas clients conduct memory-efficient zeroth-order optimization. This hybrid design not only eliminates the need for client-side BP but also enables dimension-free model aggregation, drastically lowering communication costs. Crucially, we provide a theoretical convergence analysis, demonstrating that HO-SFL mitigates the dimension-dependent convergence slowdown of zeroth-order optimization, achieving a convergence rate comparable to first-order methods. Extensive experiments on tasks across vision and language modalities validate that HO-SFL achieves convergence speeds comparable to first-order baselines while significantly reducing communication costs and client memory footprints.

Applications · Language, Speech and Dialog

Yunqi Zhang, Shiqi Yan, Zhenzhao Yuan, Wenrui Liang, Yangming Liu, Zhixiao Qi, Tianyi Zhang, Shijie Zhang, Wei-Qiang Zhang, Yongfeng Huang 等

Grounding Large Language Models (LLMs) in Knowledge Graphs (KGs) has shown significant promise for complex Question Answering (QA) tasks. Since LLMs' limited context window cannot accommodate the sheer volume of large-scale KGs, existing work usually utilizes agents to reason on real-world KGs, which follows reasoning paths derived from the queries step by step. However, the mismatch between query-derived paths and the KG's structure, stemming from users' lack of schema knowledge, usually leads the agents into dead ends. To address this problem, in this paper, we propose Backjump-on-Graph (BoG), a novel framework that empowers LLMs to retrospectively explore alternative reasoning paths at dead ends. We first propose to formalize each reasoning step with four atomic operations to create a structural scaffold that allows LLMs to revert to historical status. Next, we fine-tune the LLM with synthetic data containing the above atomic operations to instill basic backjump abilities. Finally, we leverage reinforcement learning and propose a hybrid reward function, which penalizes redundant transitions and promotes correct answers, to optimize the timing and landing nodes of backjumping. Extensive experiments on several KGQA benchmark datasets demonstrate the effectiveness of our BoG method.

Theory · Game Theory

David Yang, Yuan Gao, Tianyi Lin, Christian Kroer

We introduce, to our knowledge, the first direct second-order method for computing Nash equilibria in two-player zero-sum games. To do so, we construct a Douglas-Rachford-style splitting formulation, which we then solve with a semi-smooth Newton (SSN) method. We show that our algorithm enjoys local superlinear convergence. To augment the fast local behavior of our SSN method with global efficiency guarantees, we develop a hybrid method that combines our SSN method with the state-of-the-art first-order method for game solving, Predictive Regret Matching (PRM$^+$). Our hybrid algorithm leverages the global progress provided by PRM$^+$ while achieving a local superlinear convergence rate once it switches to SSN near a Nash equilibrium. Numerical experiments on matrix games demonstrate order-of-magnitude speedups over PRM$^+$ for high-precision solutions.