论文检索

Reinforcement Learning

Kosuke Nakanishi, Akihiro Kubo, Yuji Yasui, Shin Ishii

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable success, addressing worst-case scenarios over long time horizons requires both minimizing the agent's cumulative rewards for adversaries and training agents to counteract them through alternating learning. However, this process introduces mutual dependencies between the agent and the adversary, making interactions with the environment inefficient and hindering the development of off-policy methods.In this work, we propose a novel off-policy method that eliminates the need for additional environmental interactions by reformulating adversarial learning as a soft-constrained optimization problem. Our approach is theoretically supported by the symmetric property of policy evaluation between the agent and the adversary.The implementation is available at https://github.com/nakanakakosuke/VALT_SAC.

Reinforcement Learning · Planning

Mingde Zhao, Tristan Sylvain, Romain Laroche, Doina Precup, Yoshua Bengio

Generative models can be used in planning to propose targets corresponding to states that agents deem either likely or advantageous to experience. However, imperfections, common in learned models, lead to infeasible hallucinated targets, which can cause delusional behaviors and thus safety concerns. This work first categorizes and investigates the properties of several kinds of infeasible targets. Then, we devise a strategy to reject infeasible targets with a generic target evaluator, which trains alongside planning agents as an add-on without the need to change the behavior nor the architectures of the agent (and the generative model) it is attached to. We highlight that, without proper design, the evaluator can produce delusional estimates, rendering the strategy futile. Thus, to learn correct evaluations of infeasible targets, we propose to use a combination of learning rule, architecture, and two assistive hindsight relabeling strategies. Our experiments validate significant reductions in delusional behaviors and performance improvements for several kinds of existing planning agents.

Deep Learning · Theory

Petar Veličković, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu

A key property of reasoning systems is the ability to make sharp decisions on their input data. For contemporary AI systems, a key carrier of sharp behaviour is the softmax function, with its capability to perform differentiable query-key lookups. It is a common belief that the predictive power of networks leveraging softmax arises from "circuits" which sharply perform certain kinds of computations consistently across many diverse inputs. However, for these circuits to be robust, they would need to generalise well to arbitrary valid inputs. In this paper, we dispel this myth: even for tasks as simple as finding the maximum key, any learned circuitry must disperse as the number of items grows at test time. We attribute this to a fundamental limitation of the softmax function to robustly approximate sharp functions with increasing problem size, prove this phenomenon theoretically, and propose adaptive temperature as an ad-hoc technique for improving the sharpness of softmax at inference time.

Deep Learning · Graph Neural Networks

Biswadeep Chakraborty, Harshit Kumar, Saibal Mukhopadhyay

Graph Neural Networks (GNNs) face a critical limitation known as oversmoothing, where increasing network depth leads to homogenized node representations, severely compromising their expressiveness. We present a novel dynamical systems perspective on this challenge, revealing oversmoothing as an emergent property of GNNs' convergence to low-dimensional attractor states. Based on this insight, we introduce **DYNAMO-GAT**, which combines noise-driven covariance analysis with Anti-Hebbian learning to dynamically prune attention weights, effectively preserving distinct attractor states. We provide theoretical guarantees for DYNAMO-GAT's effectiveness and demonstrate its superior performance on benchmark datasets, consistently outperforming existing methods while requiring fewer computational resources. This work establishes a fundamental connection between dynamical systems theory and GNN behavior, providing both theoretical insights and practical solutions for deep graph learning.

Applications · Computer Vision

Wenhao Wang, Yifan Sun, Zongxin Yang, Zhentao Tan, Zhengdong Hu, Yi Yang

Text-guided image-to-image diffusion models excel in translating images based on textual prompts, allowing for precise and creative visual modifications. However, such a powerful technique can be misused for *spreading misinformation*, *infringing on copyrights*, and *evading content tracing*. This motivates us to introduce the task of origin **ID**entification for text-guided **I**mage-to-image **D**iffusion models (**ID$\mathbf{^2}$**), aiming to retrieve the original image of a given translated query. A straightforward solution to ID$^2$ involves training a specialized deep embedding model to extract and compare features from both query and reference images. However, due to *visual discrepancy* across generations produced by different diffusion models, this similarity-based approach fails when training on images from one model and testing on those from another, limiting its effectiveness in real-world applications. To solve this challenge of the proposed ID$^2$ task, we contribute the first dataset and a theoretically guaranteed method, both emphasizing generalizability. The curated dataset, **OriPID**, contains abundant **Ori**gins and guided **P**rompts, which can be used to train and test potential **ID**entification models across various diffusion models. In the method section, we first prove the *existence* of a linear transformation that minimizes the distance between the pre-trained Variational Autoencoder embeddings of generated samples and their origins. Subsequently, it is demonstrated that such a simple linear transformation can be *generalized* across different diffusion models. Experimental results show that the proposed method achieves satisfying generalization performance, significantly surpassing similarity-based methods (+31.6% mAP), even those with generalization designs. The project is available at https://id2icml.github.io.

Social Aspects · Robustness

Etienne Gauthier, Francis Bach, Michael Jordan

As platforms increasingly rely on learning algorithms, collectives may form and seek ways to influence these platforms to align with their own interests. This can be achieved by coordinated submission of altered data. To evaluate the potential impact of such behavior, it is essential to understand the computations that collectives must perform to impact platforms in this way. In particular, collectives need to make a priori assessments of the effect of the collective before taking action, as they may face potential risks when modifying their data. Moreover they need to develop implementable coordination algorithms based on quantities that can be inferred from observed data. We develop a framework that provides a theoretical and algorithmic treatment of these issues and present experimental results in a product evaluation domain.

Applications · Social Sciences

Rajiv Movva, Kenny Peng, Nikhil Garg, Jon Kleinberg, Emma Pierson

We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to produce interpretable features describing the data distribution, (2) select features that predict the target variable, and (3) generate a natural language interpretation of each feature (e.g., *mentions being surprised or shocked*) using an LLM. Each interpretation serves as a hypothesis about what predicts the target variable. Compared to baselines, our method better identifies reference hypotheses on synthetic datasets (at least +0.06 in F1) and produces more predictive hypotheses on real datasets (~twice as many significant findings), despite requiring 1-2 orders of magnitude less compute than recent LLM-based methods. HypotheSAEs also produces novel discoveries on two well-studied tasks: explaining partisan differences in Congressional speeches and identifying drivers of engagement with online headlines.

Deep Learning · Large Language Models

Harshvardhan Agarwal, Sunita Sarawagi

Large language models (LLMs) have demonstrated the capability to perform in-context learning (ICL) for completely unseen tasks in classification or language completion. Sequence to sequence (seq2seq) is another popular task category with several applications seeking quick adaptation with ICL. We present a systematic analysis of the ICL capability of LLMs on Seq2Seq tasks using a formal structured language-pair. Our study reveals a critical limitation: except for very short input sequences, ICL fails to achieve consistent learning across all output positions. This exposes a fundamental weakness of modern LLMs — their inability to effectively uncover the alignment between input and output sequences. Consequently, this limitation results in incomplete induction heads, which are essential for in-context learning of new discrete mappings.To address these limitations, we propose ICA-Tune, a method for focused fine-tuning of an LLM using in-context examples. We present a mechanistic evaluation with two accuracy probes to show how input-output alignment emerges in middle layers of an LLM without direct supervision. This alignment leads to an abrupt jump in the completeness of the induction heads in higher layers. We show that, compared to standard fine-tuning, ICA-Tune enables more sample efficient learning and better generalization to OOD instances.

General Machine Learning · Transfer, Multitask and Meta-learning

Shuai Yi, Yixiong Zou, Yuhua Li, Ruixuan Li

Cross-domain few-shot learning (CDFSL) aims to transfer knowledge from a data-sufficient source domain to data-scarce target domains. Although Vision Transformer (ViT) has shown superior capability in many vision tasks, its transferability against huge domain gaps in CDFSL is still under-explored. In this paper, we find an intriguing phenomenon: during the source-domain training, prompt tuning, as a common way to train ViT, could be harmful for the generalization of ViT in target domains, but setting them to random noises (i.e., random registers) could consistently improve target-domain performance. We then delve into this phenomenon for an interpretation. We find that learnable prompts capture domain information during the training on the source dataset, which views irrelevant visual patterns as vital cues for recognition. This can be viewed as a kind of overfitting and increases the sharpness of the loss landscapes. In contrast, random registers are essentially a novel way of perturbing attention for the sharpness-aware minimization, which helps the model find a flattened minimum in loss landscapes, increasing the transferability. Based on this phenomenon and interpretation, we further propose a simple but effective approach for CDFSL to enhance the perturbation on attention maps by adding random registers on the semantic regions of image tokens, improving the effectiveness and efficiency of random registers. Extensive experiments on four benchmarks validate our rationale and state-of-the-art performance. Codes and models are available at https://github.com/shuaiyi308/REAP.

Theory · Online Learning and Bandits

Steve Hanneke, Amirreza Shaeiri

List learning is an important topic in both theoretical and empirical machine learning research, playing a key role in the recent breakthrough result of (Brukhim et al., 2022) on the characterization of multiclass PAC learnability, as well as addressing label ambiguity in computer vision classification tasks, among others. In this paper, we study the problem of list transductive online learning. In this framework, the learner outputs a list of multiple labels for each instance rather than just one, as in traditional multiclass classification. In the realizable setting, we demonstrate a trichotomy of possible rates of the minimax number of mistakes. In particular, if the learner plays for $\text{T} \in \mathbb{N}$ rounds, its minimax number of mistakes can only be of the orders $\Theta(\text{T})$, $\Theta(\log \text{T})$, or $\Theta(1)$. This resolves an open question raised by (Hanneke et al., 2024). On the other hand, in the agnostic setting, we characterize the learnability by constructively proving the $\widetilde{\mathcal{O}}(\sqrt{\text{T}})$ upper bound on the minimax expected regret. Along the way, we also answer another open question asked by (Moran et al., 2023). To establish these results, we introduce two new combinatorial complexity dimensions, called the Level-constrained $(\mathrm{L+1})$-Littlestone dimension and Level-constrained $(\mathrm{L+1})$-Branching dimension, if the list size is $\mathrm{L} \in \mathbb{N}$. Eventually, we conclude our work by raising an open question regarding eliminating the factor list size, which seems to be a crucial step, as it has consistently appeared in previous works on this subject.

Deep Learning · Large Language Models

Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang

Post-training quantization (PTQ) of large language models (LLMs) holds the promise in reducing the prohibitive computational cost at inference time. Quantization of all weight, activation and key-value (KV) cache tensors to 4-bit without significantly degrading generalizability is challenging, due to the high quantization error caused by extreme outliers in activations. To tackle this problem, we propose ResQ, a PTQ method that pushes further the state-of-the-art. By means of principal component analysis (PCA), it identifies a low-rank subspace (in practice 1/8 of the hidden dimension) in which activation variances are highest, and keep the coefficients within this subspace in high precision, e.g.~8-bit, while quantizing the rest to 4-bit. Within each subspace, invariant random rotation is applied to further suppress outliers. We show that this is a provably optimal mixed precision quantization scheme that minimizes error. With the Llama and Qwen2.5 families of models, we demonstrate that ResQ outperforms recent uniform and mixed precision PTQ methods on a variety of benchmarks, achieving up to 33\% lower perplexity on Wikitext than the next best method SpinQuant, and upto 3X speedup over 16-bit baseline. Anonymous code repository available at https://anonymous.4open.science/r/project-resq-2142.

Reinforcement Learning · Deep RL

He ZHANG, Ming Zhou, shaopeng zhai, Ying Sun, Hui Xiong

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning.For the existing methods, they focus on improving the diversity via pure exploration, mutual information optimization and learning temporal representation. Despite they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional situations.In this work, we frame the skill discovery as a min-max game of skill generation and policy learning, proposing a regret-aware method on top of temporal representation learning that expands the discovered skill space along the direction of upgradable policy strength.The key insight behind the proposed method is that the skill discovery is adversarial to the policy learning, i.e., skills with weak strength should be further explored while less exploration for the skills with converged strength.As an implementation, we score the degree of strength convergence with regret, and guide the skill discovery with a learnable skill generator. To avoid degeneration, the skill generation comes from an upgradable population of skill generators.We conduct experiments on environments with varying complexities and dimension sizes.Empirical results show that our method outperforms baselines on both efficiency and diversity.Moreover, our method achieves 15\% zero-shot improvement on high-dimensional environments, compared to existing methods.

Deep Learning · Large Language Models

Sagnik Mukherjee, Abhinav Chinta, Takyoung Kim, Tarun Anoop Sharma, Dilek Hakkani-Tür

Chain-of-Thought (CoT) prompting enhances mathematical reasoning in large language models (LLMs) by enabling detailed step-by-step solutions. However, due to the verbosity of LLMs, the resulting reasoning chains can be long, making it harder to verify the reasoning steps and trace issues resulting from dependencies between the steps that may be farther away in the sequence of steps. Importantly, mathematical reasoning allows each step to be derived from a small set of premises, which are a subset of the preceding steps in the reasoning chain. In this paper, we present a framework that identifies the premises for each step, to improve the evaluation of reasoning. We restructure conventional linear reasoning chains into Premise Augmented Reasoning Chains (PARC) by introducing premise links, resulting in a directed acyclic graph where the nodes are the steps and the edges are the premise links. Through experiments with a PARC-based dataset that we built, namely (Premises and ERrors identification in LLMs), we demonstrate that LLMs can reliably identify premises within complex reasoning chains. In particular, even open-source LLMs achieve 90% recall in premise identification. We also show that PARC helps to identify errors in reasoning chains more reliably. The accuracy of error identification improves by 6% to 16% absolute when step-by-step verification is carried out in PARC under the premises.Our findings highlight the utility of premise-centric representations in addressing complex problem-solving tasks and open new avenues for improving the reliability of LLM-based reasoning evaluations.

Social Aspects · Safety

Edward Chang

This paper introduces a checks-and-balances framework for ethical alignment of Large Language Models (LLMs), inspired by three-branch governmental systems. It implements three independent yet interacting components: LLMs as the executive branch for knowledge generation, DIKE as the legislative branch establishing ethical guardrails, and ERIS as the judicial branch for contextual interpretation. Beyond structural separation, we address a fundamental challenge: regulating emotion to shape behaviors. Drawing from psychological theories where managing emotional responses prevents harmful behaviors, we develop a self-supervised learning pipeline that maps emotions to linguistic behaviors, enabling precise behavioral modulation through emotional conditioning. By integrating this approach with adversarial testing, our framework demonstrates how DIKE and ERIS direct linguistic behaviors toward ethical outcomes while preserving independence throughout knowledge generation, ethical oversight, and contextual interpretation.

Applications · Computer Vision

Jue Gong, Jingkai Wang, Zheng Chen, Xing Liu, Hong Gu, Yulun Zhang, Xiaokang Yang

Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark datasets. In this study, we propose a high-quality dataset automated cropping and filtering (HQ-ACF) pipeline. This pipeline leverages existing object detection datasets and other unlabeled images to automatically crop and filter high-quality human images. Using this pipeline, we constructed a person-based restoration with sophisticated objects and natural activities (*PERSONA*) dataset, which includes training, validation, and test sets. The dataset significantly surpasses other human-related datasets in both quality and content richness. Finally, we propose *OSDHuman*, a novel one-step diffusion model for human body restoration. Specifically, we propose a high-fidelity image embedder (HFIE) as the prompt generator to better guide the model with low-quality human image information, effectively avoiding misleading prompts. Experimental results show that OSDHuman outperforms existing methods in both visual quality and quantitative metrics. The dataset and code are available at: https://github.com/gobunu/OSDHuman.

Theory · Active Learning and Interactive Learning

Divya Shyamal, Jiaqi Zhang, Caroline Uhler

A _combinatorial intervention_, consisting of multiple treatments applied to a single unit with potential interactive effects, has substantial applications in fields such as biomedicine, engineering, and beyond. Given $p$ possible treatments, conducting all possible $2^p$ combinatorial interventions can be laborious and quickly becomes infeasible as $p$ increases. Here we introduce the _probabilistic factorial experimental design_, formalized from how scientists perform lab experiments. In this framework, the experimenter selects a dosage for each possible treatment and applies it to a group of units. Each unit independently receives a random combination of treatments, sampled from a product Bernoulli distribution determined by the dosages. Additionally, the experimenter can carry out such experiments over multiple rounds, adapting the design in an active manner. We address the optimal experimental design problem within a novel intervention model that imposes bounded-degree interactions between treatments. In the passive setting, we provide a closed-form solution for the near-optimal design. Our results prove that a dosage of $\frac{1}{2}$ for each treatment is optimal up to a factor of $1+O(\frac{\ln(n)}{n})$ for estimating any $k$-way interaction model, regardless of $k$, and imply that $O\big(kp^{3k}\ln(p)\big)$ observations are required to accurately estimate this model. For the multi-round setting, we provide a near-optimal acquisition function that can be numerically optimized. We also explore several extensions of the design problem and finally validate our findings through simulations.

Reinforcement Learning · Deep RL

Nikola Milosevic, Johannes Müller, Nico Scherf

Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward maximization or allow unsafe training. We introduce Constrained Trust Region Policy Optimization (C-TRPO), which reshapes the policy space geometry to ensure trust regions contain only safe policies, guaranteeing constraint satisfaction throughout training. We analyze its theoretical properties and connections to TRPO, Natural Policy Gradient (NPG), and Constrained Policy Optimization (CPO). Experiments show that C-TRPO reduces constraint violations while maintaining competitive returns.

Deep Learning · Large Language Models

Rui Yang, Hanyang(Jeremy) Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Koripella, Marziyeh Movahedi, Manling Li 等

Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents.EmbodiedBench features: (1) a diverse set of 1,128 testing tasks across four environments, ranging from high-level semantic tasks (e.g., household) to low-level tasks involving atomic actions (e.g., navigation and manipulation); and (2) six meticulously curated subsets evaluating essential agent capabilities like commonsense reasoning, complex instruction understanding, spatial awareness, visual perception, and long-term planning.Through extensive experiments, we evaluated 24 leading proprietary and open-source MLLMs within EmbodiedBench. Our findings reveal that: MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only $28.9\\%$ on average. EmbodiedBench provides a multifaceted standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance MLLM-based embodied agents. Our code and dataset are available at [https://embodiedbench.github.io](https://embodiedbench.github.io).

Reinforcement Learning

Vincenzo De Paola, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

Parallel data collection has redefined Reinforcement Learning (RL), unlocking unprecedented efficiency and powering breakthroughs in large-scale real-world applications. In this paradigm, $N$ identical agents operate in $N$ replicas of an environment simulator, accelerating data collection by a factor of $N$. A critical question arises: *Does specializing the policies of the parallel agents hold the key to surpass the $N$ factor acceleration?*In this paper, we introduce a novel learning framework that maximizes the entropy of collected data in a parallel setting. Our approach carefully balances the entropy of individual agents with inter-agent diversity, effectively minimizing redundancies. The latter idea is implemented with a centralized policy gradient method, which shows promise when evaluated empirically against systems of identical agents, as well as synergy with batch RL techniques that can exploit data diversity.Finally, we provide an original concentration analysis that shows faster rates for specialized parallel sampling distributions, which supports our methodology and may be of independent interest.

Deep Learning · Large Language Models

Ruida Wang, Rui Pan, Yuxin Li, Jipeng Zhang, Yizhen Jia, Shizhe Diao, Renjie Pi, Junjie Hu, Tong Zhang

Solving mathematical problems using computer-verifiable languages like Lean has significantly impacted the mathematical and computer science communities. State-of-the-art methods utilize a single Large Language Model (LLM) to generate complete proof or perform tree search, but they fail to balance these tasks. We propose **MA-LoT**: *Model-CollAboration Lean-based Long Chain-of-Thought*, a comprehensive framework for Lean4 theorem proving to solve this issue. It separates the cognition tasks of general NL for whole-proof generation and error analysis for proof correction using the model-collaboration method. We achieve this by structured interaction of the LLM and Lean4 verifier in Long CoT. To implement the framework, we propose the novel *LoT-Transfer Learning* training-inference pipeline, which enables the Long CoT thinking capability to LLMs without special data annotation. Extensive experiment shows that our framework achieves a **61.07%** accuracy rate on the Lean4 version of the MiniF2F-Test dataset, largely outperforming DeepSeek-V3 (33.61%), single-model tree search (InternLM-Step-Prover, 50.70%), and whole-proof generation (Godel-Prover, 55.33%) baselines. Furthermore, our findings highlight the potential of combining Long CoT with formal verification for a more insightful generation in a broader perspective.