ICLR 2025 论文列表

Large Language Models (LLMs) have made significant strides in natural language processing, and a precise understanding of the internal mechanisms driving their success is essential. In this work, we analyze the trajectories of token embeddings as they pass through transformer blocks, linearizing the system along these trajectories through their Jacobian matrices. By examining the relationships between these block Jacobians, we uncover the phenomenon of **transformer block coupling** in a multitude of LLMs, characterized by the coupling of their top singular vectors across tokens and depth. Our findings reveal that coupling *positively correlates* with model performance, and that this relationship is stronger than with other hyperparameters such as parameter count, model depth, and embedding dimension. We further investigate how these properties emerge during training, observing a progressive development of coupling, increased linearity, and layer-wise exponential growth in token trajectories. Additionally, experiments with Vision Transformers (ViTs) corroborate the emergence of coupling and its relationship with generalization, reinforcing our findings in LLMs. Collectively, these insights offer a novel perspective on token interactions in transformers, opening new directions for studying their mechanisms as well as improving training and generalization.

Chemical reasoning usually involves complex, multi-step processes that demand precise calculations, where even minor errors can lead to cascading failures. Furthermore, large language models (LLMs) encounter difficulties handling domain-specific formulas, executing reasoning steps accurately, and integrating code ef- effectively when tackling chemical reasoning tasks. To address these challenges, we present ChemAgent, a novel framework designed to improve the performance of LLMs through a dynamic, self-updating library. This library is developed by decomposing chemical tasks into sub-tasks and compiling these sub-tasks into a structured collection that can be referenced for future queries. Then, when presented with a new problem, ChemAgent retrieves and refines pertinent information from the library, which we call memory, facilitating effective task decomposition and the generation of solutions. Our method designs three types of memory and a library-enhanced reasoning component, enabling LLMs to improve over time through experience. Experimental results on four chemical reasoning datasets from SciBench demonstrate that ChemAgent achieves performance gains of up to 46% (GPT-4), significantly outperforming existing methods. Our findings suggest substantial potential for future applications, including tasks such as drug discovery and materials science. Our code can be found at https://github.com/gersteinlab/ChemAgent.

We address the challenge of minimizing "true risk" in multi-node distributed learning.\footnote{We use the term node to refer to a client, FPGA, APU, CPU, GPU, or worker.} These systems are frequently exposed to both inter-node and intra-node "label shifts", which present a critical obstacle to effectively optimizing model performance while ensuring that data remains confined to each node. To tackle this, we propose the Versatile Robust Label Shift (VRLS) method, which enhances the maximum likelihood estimation of the test-to-train label importance ratio. VRLS incorporates Shannon entropy-based regularization and adjusts the importance ratio during training to better handle label shifts at the test time. In multi-node learning environments, VRLS further extends its capabilities by learning and adapting importance ratios across nodes, effectively mitigating label shifts and improving overall model performance. Experiments conducted on MNIST, Fashion MNIST, and CIFAR-10 demonstrate the effectiveness of VRLS, outperforming baselines by up to 20\% in imbalanced settings. These results highlight the significant improvements VRLS offers in addressing label shifts. Our theoretical analysis further supports this by establishing high-probability bounds on estimation errors.

Implementing Boolean functions with circuits consisting of logic gates is fundamental in digital computer design. However, the implemented circuit must be exactly equivalent, which hinders generative neural approaches on this task due to their occasionally wrong predictions. In this study, we introduce a generative neural model, the “Circuit Transformer”, which eliminates such wrong predictions and produces logic circuits strictly equivalent to given Boolean functions. The main idea is a carefully designed decoding mechanism that builds a circuit step-by-step by generating tokens, which has beneficial “cutoff properties” that block a candidate token once it invalidate equivalence. In such a way, the proposed model works similar to typical LLMs while logical equivalence is strictly preserved. A Markov decision process formulation is also proposed for optimizing certain objectives of circuits. Experimentally, we trained an 88-million-parameter Circuit Transformer to generate equivalent yet more compact forms of input circuits, outperforming existing neural approaches on both synthetic and real world benchmarks, without any violation of equivalence constraints. Code: https://github.com/snowkylin/circuit-transformer

Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. However, the current evaluation of RMs may not directly correspond to their alignment performance due to the limited distribution of evaluation data and evaluation methods that are not closely related to alignment objectives. To address these limitations, we propose RMB, a comprehensive RM benchmark that covers over 49 real-world scenarios and includes both pairwise and Best-of-N (BoN) evaluations to better reflect the effectiveness of RMs in guiding alignment optimization. We demonstrate a positive correlation between our benchmark and the downstream alignment task performance. Based on our benchmark, we conduct extensive analysis on the state-of-the-art RMs, revealing their generalization defects that were not discovered by previous benchmarks, and highlighting the potential of generative RMs. Furthermore, we delve into open questions in reward models, specifically examining the effectiveness of majority voting for the evaluation of reward models and analyzing the impact factors of generative RMs, including the influence of evaluation criteria and instructing methods. We will release our evaluation code and datasets upon publication.

Centralized Training and Decentralized Execution (CTDE) is a widely adopted paradigm to solve cooperative multi-agent reinforcement learning (MARL) problems. Despite the successes achieved with CTDE, partial observability still limits cooperation among agents. While previous studies have attempted to overcome this challenge through communication, direct information exchanges could be restricted and introduce additional constraints. Alternatively, if an agent can infer the global information solely from local observations, it can obtain a global view without the need for communication. To this end, we propose the Multi-Agent Masked Auto-Encoder (MA$^2$E), which utilizes the masked auto-encoder architecture to infer the information of other agents from partial observations. By employing masking to learn to reconstruct global information, MA$^2$E serves as an inference module for individual agents within the CTDE framework. MA$^2$E can be easily integrated into existing MARL algorithms and has been experimentally proven to be effective across a wide range of environments and algorithms.

We study the Differential Privacy (DP) guarantee of hidden-state Noisy-SGD algorithms over a bounded domain. Standard privacy analysis for Noisy-SGD assumes all internal states are revealed, which leads to a divergent R\'enyi DP bound with respect to the number of iterations. Ye & Shokri (2022) and Altschuler & Talwar (2022) proved convergent bounds for smooth (strongly) convex losses, and raise open questions about whether these assumptions can be relaxed. We provide positive answers by proving convergent R\'enyi DP bound for non-convex non-smooth losses, where we show that requiring losses to have H\"older continuous gradient is sufficient. We also provide a strictly better privacy bound compared to state-of-the-art results for smooth strongly convex losses. Our analysis relies on the improvement of shifted divergence analysis in multiple aspects, including forward Wasserstein distance tracking, identifying the optimal shifts allocation, and the H\"older reduction lemma. Our results further elucidate the benefit of hidden-state analysis for DP and its applicability.

As Graph Neural Networks (GNNs) become more pervasive, it becomes paramount to build reliable tools for explaining their predictions. A core desideratum is that explanations are *faithful*, i.e., that they portray an accurate picture of the GNN's reasoning process. However, a number of different faithfulness metrics exist, begging the question of what is faithfulness exactly and how to achieve it. We make three key contributions. We begin by showing that *existing metrics are not interchangeable* -- i.e., explanations attaining high faithfulness according to one metric may be unfaithful according to others -- and can *systematically ignore important properties of explanations*. We proceed to show that, surprisingly, *optimizing for faithfulness is not always a sensible design goal*. Specifically, we prove that for injective regular GNN architectures, perfectly faithful explanations are completely uninformative. This does not apply to modular GNNs, such as self-explainable and domain-invariant architectures, prompting us to study the relationship between architectural choices and faithfulness. Finally, we show that *faithfulness is tightly linked to out-of-distribution generalization*, in that simply ensuring that a GNN can correctly recognize the domain-invariant subgraph, as prescribed by the literature, does not guarantee that it is invariant unless this subgraph is also faithful. All our code can be found in the supplementary material.

Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affecting the evaluation quality. Our study reveals that task transferability and relevance provide critical information to identify the most representative subset of tasks via optimizing a facility location function. We propose a practically efficient metric for estimating the transferability between two tasks via in-context learning (ICL). By analyzing the pairwise transferability, we can reduce tasks in a modern LLM benchmark (e.g., MMLU or FLAN) to 5\% while inducing only a $<4$\% difference to the evaluation on the original benchmark. Compared to prior works, our method is training-free, gradient-free, and highly efficient requiring ICL only.

CLIP has achieved great success in visual representation learning and is becoming an important plug-in component for many large multi-modal models like LLaVA and DALL-E. However, the lack of interpretability caused by the intricate image encoder architecture and training process restricts its wider use in high-stake decision making applications. In this work, we propose an unsupervised adversarial fine-tuning (AFT) with norm-regularization to enhance the visual interpretability of CLIP. We provide theoretical analysis showing that AFT has implicit regularization that enforces the image encoder to encode the input features sparsely, directing the network's focus towards meaningful features. Evaluations by both feature attribution techniques and network dissection offer convincing evidence that the visual interpretability of CLIP has significant improvements. With AFT, the image encoder prioritizes pertinent input features, and the neuron within the encoder exhibits better alignment with human-understandable concepts. Moreover, these effects are generalizable to out-of-distribution datasets and can be transferred to downstream tasks. Additionally, AFT enhances the visual interpretability of derived large vision-language models that incorporate the pre-trained CLIP an integral component. The code of this paper is available at [the CLIP_AFT GitHub repository](https://github.com/peterant330/CLIP_AFT).

As large language models (LLMs) grow more powerful, they also become more difficult to trust. They could be either aligned with human intentions, or exhibit "subversive misalignment" -- introducing subtle errors that bypass safety checks. Although individual errors may not immediately cause harm, each increases the risk of an eventual safety failure. With this uncertainty, model deployment often grapples with the tradeoff between ensuring safety and harnessing the capabilities of untrusted models. In this work, we introduce the ``Diffuse Risk Management'' problem, aiming to balance the average-case safety and usefulness in the deployment of untrusted models over a large sequence of tasks. We approach this problem by developing a two-level framework: the single-task level (micro-protocol) and the whole-scenario level (macro-protocol). At the single-task level, we develop various \textit{micro}-protocols that use a less capable, but extensively tested (trusted) model to harness and monitor the untrusted model. At the whole-scenario level, we find an optimal \textit{macro}-protocol that uses an adaptive estimate of the untrusted model's risk to choose between micro-protocols. To evaluate the robustness of our method, we follow \textit{control evaluations} in a code generation testbed, which involves a red team attempting to generate subtly backdoored code with an LLM whose deployment is safeguarded by a blue team. Experiment results show that our approach retains 99.6\% usefulness of the untrusted model while ensuring near-perfect safety, significantly outperforming existing deployment methods. Our approach also demonstrates robustness when the trusted and untrusted models have a large capability gap. Our findings demonstrate the promise of managing diffuse risks in the deployment of increasingly capable but untrusted LLMs.

Data-driven modeling of dynamical systems is a crucial area of machine learning. In many scenarios, a thorough understanding of the model’s behavior becomes essential for practical applications. For instance, understanding the behavior of a pharmacokinetic model, constructed as part of drug development, may allow us to both verify its biological plausibility (e.g., the drug concentration curve is non-negative and decays to zero in the long term) and to design dosing guidelines (e.g., by looking at the peak concentration and its timing). Discovery of closed-form ordinary differential equations (ODEs) can be employed to obtain such insights by finding a compact mathematical equation and then analyzing it (a two-step approach). However, its widespread use is currently hindered because the analysis process may be time-consuming, requiring substantial mathematical expertise, or even impossible if the equation is too complex. Moreover, if the found equation's behavior does not satisfy the requirements, editing it or influencing the discovery algorithms to rectify it is challenging as the link between the symbolic form of an ODE and its behavior can be elusive. This paper proposes a conceptual shift to modeling low-dimensional dynamical systems by departing from the traditional two-step modeling process. Instead of first discovering a closed-form equation and then analyzing it, our approach, direct semantic modeling, predicts the semantic representation of the dynamical system (i.e., description of its behavior) directly from data, bypassing the need for complex post-hoc analysis. This direct approach also allows the incorporation of intuitive inductive biases into the optimization algorithm and editing the model's behavior directly, ensuring that the model meets the desired specifications. Our approach not only simplifies the modeling pipeline but also enhances the transparency and flexibility of the resulting models compared to traditional closed-form ODEs.

Sequence labeling problems arise in several real-world applications such as healthcare and robotics. In many such applications, sequence data are irregularly sampled and are of varying complexities. Recently, efforts have been made to develop neural ODE-based architectures to model the evolution of hidden states continuously in time, to address irregularly sampled sequence data. However, they assume a fixed architectural depth and limit their flexibility to adapt to data sets with varying complexities. We propose the neural wave equation, a novel deep learning method inspired by the wave equation, to address this through continuous modeling of depth. Neural Wave Equation models the evolution of hidden states continuously across time as well as depth by using a non-homogeneous wave equation parameterized by a neural network. Through d'Alembert's analytical solution of the wave equation, we also show that the neural wave equation provides denser connections across the hidden states, allowing for better modeling capability. We conduct experiments on several sequence labeling problems involving irregularly sampled sequence data and demonstrate the superior performance of the proposed neural wave equation model.

Evaluation has traditionally focused on ranking candidates for a specific skill. Modern generalist models, such as Large Language Models (LLMs), decidedly outpace this paradigm. Open-ended evaluation systems, where candidate models are compared on user-submitted prompts, have emerged as a popular solution. Despite their many advantages, we show that the current Elo-based rating systems can be susceptible to and even reinforce biases in data, intentional or accidental, due to their sensitivity to redundancies. To address this issue, we propose evaluation as a 3-player game, and introduce novel game-theoretic solution concepts to ensure robustness to redundancy. We show that our method leads to intuitive ratings and provide insights into the competitive landscape of LLM development.

We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pretrained diffusion models, while avoiding their text-centric conditioning bias. We also incorporate an additional guidance loss into our architecture to align cross-attention from adapter layers with slot attention. This enhances the alignment of our model with the objects in the input image without using external supervision. Experimental results show that our method outperforms state-of-the-art techniques in object discovery and image generation tasks across multiple datasets, including those with real images. Furthermore, we demonstrate through experiments that our method performs remarkably well on complex real-world images for compositional generation, in contrast to other slot-based generative methods in the literature. The project page can be found at https://kaanakan.github.io/SlotAdapt/

Photoplethysmography (PPG) is the leading non-invasive technique for monitoring biosignals and cardiovascular health, with widespread adoption in both clinical settings and consumer wearable devices. While machine learning models trained on PPG signals have shown promise, they tend to be task-specific and struggle with generalization. Current research is limited by the use of single-device datasets, insufficient exploration of out-of-domain generalization, and a lack of publicly available models, which hampers reproducibility. To address these limitations, we present PaPaGei, the first open foundation model for PPG signals. The model is pre-trained on over 57,000 hours of data, comprising 20 million unlabeled PPG segments from publicly available datasets. We introduce a novel representation learning approach that leverages domain knowledge of PPG signal morphology across individuals, enabling the capture of richer representations compared to traditional contrastive learning methods. We evaluate PaPaGei against state-of-the-art time-series foundation models and self-supervised learning benchmarks across 20 tasks from 10 diverse datasets, spanning cardiovascular health, sleep disorders, pregnancy monitoring, and wellbeing assessment. Our model demonstrates superior performance, improving classification and regression metrics by 6.3% and 2.9% respectively in at least 14 tasks. Notably, PaPaGei achieves these results while being more data- and parameter-efficient, outperforming models that are 70x larger. Beyond accuracy, we examine model robustness across different skin tones, establishing a benchmark for bias evaluation in future models. PaPaGei can serve as both a feature extractor and an encoder for multimodal models, opening up new opportunities for multimodal health monitoring. Models, data, and code are available at: https://github.com/nokia-bell-labs/papagei-foundation-model

Adversarial Imitation Learning is traditionally framed as a two-player zero-sum game between a learner and an adversarially chosen cost function, and can therefore be thought of as the sequential generalization of a Generative Adversarial Network (GAN). However, in recent years, diffusion models have emerged as a non-adversarial alternative to GANs that merely require training a score function via regression, yet produce generations of higher quality. In response, we investigate how to lift insights from diffusion modeling to the sequential setting. We propose diffusing states and performing *score-matching* along diffused states to measure the discrepancy between the expert's and learner's states. Thus, our approach only requires training score functions to predict noises via standard regression, making it significantly easier and more stable to train than adversarial methods. Theoretically, we prove first- and second-order instance-dependent bounds with linear scaling in the horizon, proving that our approach avoids the compounding errors that stymie offline approaches to imitation learning. Empirically, we show our approach outperforms both GAN-style imitation learning baselines and discriminator-free imitation learning baselines across various continuous control problems, including complex tasks like controlling humanoids to walk, sit, crawl, and navigate through obstacles.

RAG enables LLMs to easily incorporate external data, raising concerns for data owners regarding unauthorized usage of their content. The challenge of detecting such unauthorized usage remains underexplored, with datasets and methods from adjacent fields being ill-suited for its study. We take several steps to bridge this gap. First, we formalize this problem as (black-box) RAG Dataset Inference (RAG-DI). We then introduce a novel dataset designed for realistic benchmarking of RAG-DI methods, alongside a set of baselines. Finally, we propose Ward, a method for RAG-DI based on LLM watermarks that equips data owners with rigorous statistical guarantees regarding their dataset's misuse in RAG corpora. Ward consistently outperforms all baselines, achieving higher accuracy, superior query efficiency and robustness. Our work provides a foundation for future studies of RAG-DI and highlights LLM watermarks as a promising approach to this problem.

Dynamic graphs capture evolving interactions between entities, such as in social networks, online learning platforms, and crowdsourcing projects. For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream technique. However, they are generally pre-trained on the link prediction task, leaving a significant gap from the objectives of downstream tasks such as node classification. To bridge the gap, prompt-based learning has gained traction on graphs, but most existing efforts focus on static graphs, neglecting the evolution of dynamic graphs. In this paper, we propose DyGPrompt, a novel pre-training and prompt learning framework for dynamic graph modeling. First, we design dual prompts to address the gap in both task objectives and temporal variations across pre-training and downstream tasks. Second, we recognize that node and time patterns often characterize each other, and propose dual condition-nets to model the evolving node-time patterns in downstream tasks. Finally, we thoroughly evaluate and analyze DyGPrompt through extensive experiments on four public datasets.