ICLR 2025 论文列表

Recent research pinpoints that different diffusion methods and architectures trained on the same dataset produce similar results for the same input noise. This property suggests that they have some preferable noises for a given sample. By visualizing the noise-sample pairs of rectified flow models and stable diffusion models in two-dimensional spaces, we observe that the preferable paths, connecting preferable noises to the corresponding samples, are better organized with significant fewer crossings comparing with the random paths, connecting random noises to training samples. In high-dimensional space, paths rarely intersect. The path crossings in two-dimensional spaces indicate the shorter inter-path distance in the corresponding high-dimensional spaces. Inspired by this observation, we propose the Distance-Aware Noise-Sample Matching (DANSM) method to lengthen the inter-path distance for speeding up the model training. DANSM is derived from rectified flow models, which allow using a closed-form formula to calculate the inter-path distance. To further simplify the optimization, we derive the relationship between inter-path distance and path length, and use the latter in the optimization surrogate. DANSM is evaluated on both image and latent spaces by rectified flow models and diffusion models. The experimental results show that DANSM can significantly improve the training speed by 30\% $\sim$ 40\% without sacrificing the generation quality.

State-space models (SSMs) that utilize linear, time-invariant (LTI) systems are known for their effectiveness in learning long sequences. To achieve state-of-the-art performance, an SSM often needs a specifically designed initialization, and the training of state matrices is on a logarithmic scale with a very small learning rate. To understand these choices from a unified perspective, we view SSMs through the lens of Hankel operator theory. Building upon it, we develop a new parameterization scheme, called HOPE, for LTI systems that utilizes Markov parameters within Hankel operators. Our approach helps improve the initialization and training stability, leading to a more robust parameterization. We efficiently implement these innovations by nonuniformly sampling the transfer functions of LTI systems, and they require fewer parameters compared to canonical SSMs. When benchmarked against HiPPO-initialized models such as S4 and S4D, an SSM parameterized by Hankel operators demonstrates improved performance on Long-Range Arena (LRA) tasks. Moreover, our new parameterization endows the SSM with non-decaying memory within a fixed time window, which is empirically corroborated by a sequential CIFAR-10 task with padded noise.

Large language models demonstrate impressive performance on downstream tasks, yet requiring extensive resource consumption when fully fine-tuning all parameters. To mitigate this, Parameter Efficient Fine-Tuning (PEFT) strategies, such as LoRA, have been developed. In this paper, we delve into the concept of task-specific directions (TSDs)—critical for transitioning large models from pretrained states to task-specific enhancements in PEFT. We propose a framework to clearly define these directions and explore their properties, and practical utilization challenges. We then introduce a novel approach, LoRA-Dash, which aims to maximize the impact of TSDs during the fine-tuning process, thereby enhancing model performance on targeted tasks. Extensive experiments have conclusively demonstrated the effectiveness of LoRA-Dash, and in-depth analyses further reveal the underlying mechanisms of LoRA-Dash.

How to balance between exploration and exploitation in an uncertain environment is a central challenge in reinforcement learning. In contrast, humans and animals have demonstrated superior exploration efficiency in novel environments. To understand how the brain’s neural network controls exploration under uncertainty, we analyzed the dynamical systems model of a biological neural network that controls explore-exploit decisions during foraging. Mathematically, this model (named the Brain Bandit Net, or BBN) is a special type of stochastic continuous Hopfield network. We show through theory and simulation that BBN can perform posterior sampling of action values with a tunable bias towards or against uncertain options. We then demonstrate that, in multi-armed bandit (MAB) tasks, BBN can generate probabilistic choice behavior with a flexible uncertainty bias resembling human and animal choice patterns. In addition to its high efficiency in MAB tasks, BBN can also be embedded with reinforcement learning algorithms to accelerate learning in MDP tasks. Altogether, our findings reveal the theoretical foundation for efficient exploration in biological neural networks and propose a general, brain-inspired algorithm for enhancing exploration in RL.

Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose a **C**ontrastive **L**anguage-**A**ction **V**ideo Learn**er** (**CLAVER**), designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to the alignment of dynamic action behaviors and abstract verbs. Specifically, we introduce a novel Kronecker mask attention for temporal modeling. Our tailored Kronecker mask offers three benefits 1) it expands the temporal receptive field for each token, 2) it serves as an effective spatiotemporal heterogeneity inductive bias, mitigating the issue of spatiotemporal homogenization, and 3) it can be seamlessly plugged into transformer-based models. Regarding the textual branch, we leverage large language models to generate diverse, sentence-level and semantically rich interpretive prompts of actions, which shift the model's focus towards the verb comprehension. Extensive experiments on various benchmarks and learning scenarios demonstrate the superiority and generality of our approach. The code will be available soon.

As large language models (LLMs) increasingly become central to various applications and interact with diverse user populations, ensuring their reliable and consistent performance is becoming more important. This paper explores a critical issue in assessing the reliability of LLMs: the consistency between their words and deeds. To quantitatively explore this consistency, we developed a novel evaluation benchmark called the Words and Deeds Consistency Test (WDCT). The benchmark establishes a strict correspondence between word-based and deed-based questions across different domains, including opinion vs. action, non-ethical value vs. action, ethical value vs. action, and theory vs. application. The evaluation results reveal a widespread inconsistency between words and deeds across different LLMs and domains. Subsequently, we conducted experiments with either word alignment or deed alignment to observe their impact on the other aspect. The experimental results indicate that alignment only on words or deeds poorly and unpredictably influences the other aspect. This supports our hypothesis that the underlying knowledge guiding LLMs' word or deed choices is not contained within a unified space. Dataset and code are available at [https://github.com/icip-cas/Word-Deed-Consistency-Test](https://github.com/icip-cas/Word-Deed-Consistency-Test).

The increasing deployment of large language model (LLM)-based chatbots has raised concerns regarding fairness. Fairness issues in LLMs may result in serious consequences, such as bias amplification, discrimination, and harm to minority groups. Many efforts are dedicated to evaluating and mitigating biases in LLMs. However, existing fairness benchmarks mainly focus on single-turn dialogues, while multi-turn scenarios, which better reflect real-world conversations, pose greater challenges due to conversational complexity and risk for bias accumulation. In this paper, we introduce a comprehensive benchmark for fairness of LLMs in multi-turn scenarios, **FairMT-Bench**. Specifically, We propose a task taxonomy to evaluate fairness of LLMs cross three stages: context understanding, interaction fairness, and fairness trade-offs, each comprising two tasks. To ensure coverage of diverse bias types and attributes, our multi-turn dialogue dataset FairMT-10K is constructed by integrating data from established fairness benchmarks. For evaluation, we employ GPT-4 along with bias classifiers like Llama-Guard-3, and human annotators to ensure robustness. Our experiments and analysis on FairMT-10K reveal that in multi-turn dialogue scenarios, LLMs are more prone to generating biased responses, showing significant variation in performance across different tasks and models. Based on these findings, we develop a more challenging dataset, FairMT-1K, and test 15 current state-of-the-art (SOTA) LLMs on this dataset. The results highlight the current state of fairness in LLMs and demonstrate the value of this benchmark for evaluating fairness of LLMs in more realistic multi-turn dialogue contexts. This underscores the need for future works to enhance LLM fairness and incorporate FairMT-1K in such efforts. Our code and dataset are available at https://github.com/FanZT6/FairMT-bench.

Prior work has demonstrated a consistent tendency in neural networks engaged in continual learning tasks, wherein intermediate task similarity results in the highest levels of catastrophic interference. This phenomenon is attributed to the network's tendency to reuse learned features across tasks. However, this explanation heavily relies on the premise that neuron specialisation occurs, i.e. the emergence of localised representations. Our investigation challenges the validity of this assumption. Using theoretical frameworks for the analysis of neural networks, we show a strong dependence of specialisation on the initial condition. More precisely, we show that weight imbalance and high weight entropy can favour specialised solutions. We then apply these insights in the context of continual learning, first showing the emergence of a monotonic relation between task-similarity and forgetting in non-specialised networks. Finally, we show that specialization by weight imbalance is beneficial on the commonly employed elastic weight consolidation regularisation technique.

Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In this work, we aim to investigate the vulnerability of LLMs under prompt-based and fine-tuning-based gaslighting attacks. Therefore, we propose a two-stage framework DeepCoG designed to: 1) elicit gaslighting plans from LLMs with the proposed DeepGaslighting prompting template, and 2) acquire gaslighting conversations from LLMs through our Chain-of-Gaslighting method. The gaslighting conversation dataset along with a corresponding safe dataset is applied to fine-tuning-based attacks on open-source LLMs and anti-gaslighting safety alignment on these LLMs. Experiments demonstrate that both prompt-based and fine-tuning-based attacks transform three open-source LLMs into gaslighters. In contrast, we advanced three safety alignment strategies to strengthen~(by $12.05\%$) the safety guardrail of LLMs. Our safety alignment strategies have minimal impacts on the utility of LLMs. Empirical studies indicate that an LLM may be a potential gaslighter, even if it passed the harmfulness test on general dangerous queries.

Model merging has emerged as a crucial technique in Deep Learning, enabling the integration of multiple models into a unified system while preserving performance and scalability. In this respect, the compositional properties of low-rank adaptation techniques (e.g., LoRA) have proven beneficial, as simple averaging LoRA modules yields a single model that mostly integrates the capabilities of all individual modules. Building on LoRA, we take a step further by imposing that the merged model matches the responses of all learned modules. Solving this ob- jective in closed form yields an indeterminate system with A and B as unknown variables, indicating the existence of infinitely many closed-form solutions. To address this challenge, we introduce LoRM, an alternating optimization strategy that trains one LoRA matrix at a time. This allows solving for each unknown variable individually, thus finding a unique solution. We apply our proposed methodology to Federated Class-Incremental Learning (FCIL), ensuring alignment of model responses both between clients and across tasks. Our method demonstrates state-of-the-art performance across a range of FCIL scenarios. The code to reproduce our experiments is available at github.com/aimagelab/fed-mammoth.

We study min-max algorithms to solve zero-sum differential games on Riemannian manifold. Based on the notions of differential Stackelberg equilibrium and differential Nash equilibrium on Riemannian manifold, we analyze the local convergence of two representative deterministic simultaneous algorithms $\tau$-GDA and $\tau$-SGA to such equilibria. Sufficient conditions are obtained to establish the linear convergence rate of $\tau$-GDA based on the Ostrowski theorem on manifold and spectral analysis. To avoid strong rotational dynamics in $\tau$-GDA, $\tau$-SGA is extended from the symplectic gradient-adjustment method in Euclidean space. We analyze an asymptotic approximation of $\tau$-SGA when the learning rate ratio $\tau$ is big. In some cases, it can achieve a faster convergence rate to differential Stackelberg equilibrium compared to $\tau$-GDA. We show numerically how the insights obtained from the convergence analysis may improve the training of orthogonal Wasserstein GANs using stochastic $\tau$-GDA and $\tau$-SGA on simple benchmarks.

LiDAR novel view synthesis (NVS) has emerged as a novel task within LiDAR simulation, offering valuable simulated point cloud data from novel viewpoints to aid in autonomous driving systems. However, existing LiDAR NVS methods typically rely on neural radiance fields (NeRF) as their 3D representation, which incurs significant computational costs in both training and rendering. Moreover, NeRF and its variants are designed for symmetrical scenes, making them ill-suited for driving scenarios. To address these challenges, we propose GS-LiDAR, a novel framework for generating realistic LiDAR point clouds with panoramic Gaussian splatting. Our approach employs 2D Gaussian primitives with periodic vibration properties, allowing for precise geometric reconstruction of both static and dynamic elements in driving scenarios. We further introduce a novel panoramic rendering technique with explicit ray-splat intersection, guided by panoramic LiDAR supervision. By incorporating intensity and ray-drop spherical harmonic (SH) coefficients into the Gaussian primitives, we enhance the realism of the rendered point clouds. Extensive experiments on KITTI-360 and nuScenes demonstrate the superiority of our method in terms of quantitative metrics, visual quality, as well as training and rendering efficiency.

Reconstructing high-quality images under low bitrates conditions presents a challenge, and previous methods have made this task feasible by leveraging the priors of diffusion models. However, the effective exploration of pre-trained latent diffusion models and semantic information integration in image compression tasks still needs further study. To address this issue, we introduce Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement (DiffPC), a two-stage image compression framework based on stable diffusion. DiffPC efficiently encodes low-level image information, enabling the highly realistic reconstruction of the original image by leveraging high-level semantic features and the prior knowledge inherent in diffusion models. Specifically, DiffPC utilizes a multi-feature compressor to represent crucial low-level information with minimal bitrates and employs pre-embedding to acquire more robust hybrid semantics, thereby providing additional context for the decoding end. Furthermore, we have devised a control module tailored for image compression tasks, ensuring structural and textural consistency in reconstruction even at low bitrates and preventing decoding collapses induced by condition leakage. Extensive experiments demonstrate that our method achieves state-of-the-art perceptual fidelity and surpasses previous perceptual image compression methods by a significant margin in statistical fidelity.

Designing reward functions in Reinforcement Learning (RL) often demands significant task-specific expertise. Offline Preference-based Reinforcement Learning (PbRL) provides an effective alternative to address the complexity of reward design by learning policies from offline datasets that contain human preferences between trajectory pairs. Existing offline PbRL studies typically model a reward function by maximizing its likelihood of generating the observed human preferences. However, due to the varying number of samples within the limited dataset, less frequently compared trajectories exhibit greater uncertainty, which potentially leads to unreliable behaviors during reward and policy updates. To solve this issue, in this work, we introduce Uncertainty-Aware PbRL (UA-PbRL) to learn a distributional reward model and a risk-sensitive policy from an offline preference dataset. Our approach employs a Maximum A Posteriori (MAP) objective to update trajectory rewards and incorporates an informative prior to account for the uncertainties. Building upon this reward update, we propose a generative reward model to capture the reward distribution, utilizing the offline distributional Bellman operator and the Conditional Value-at-Risk (CVaR) metric to train a risk-sensitive policy. Experimental results demonstrate that UA-PbRL effectively identifies and avoids states with high uncertainty, facilitating risk-averse behaviors across various tasks, including robot control and language model alignment. The code is available at https://github.com/Jasonxu1225/UA-PbRL.

Enabling robots to learn novel tasks in a data-efficient manner is a long-standing challenge. Common strategies involve carefully leveraging prior experiences, especially transition data collected on related tasks. Although much progress has been made for general pick-and-place manipulation, far fewer studies have investigated contact-rich assembly tasks, where precise control is essential. We introduce SRSA} (Skill Retrieval and Skill Adaptation), a novel framework designed to address this problem by utilizing a pre-existing skill library containing policies for diverse assembly tasks. The challenge lies in identifying which skill from the library is most relevant for fine-tuning on a new task. Our key hypothesis is that skills showing higher zero-shot success rates on a new task are better suited for rapid and effective fine-tuning on that task. To this end, we propose to predict the transfer success for all skills in the skill library on a novel task, and then use this prediction to guide the skill retrieval process. We establish a framework that jointly captures features of object geometry, physical dynamics, and expert actions to represent the tasks, allowing us to efficiently learn the transfer success predictor. Extensive experiments demonstrate that SRSA significantly outperforms the leading baseline. When retrieving and fine-tuning skills on unseen tasks, SRSA achieves a 19% relative improvement in success rate, exhibits 2.6x lower standard deviation across random seeds, and requires 2.4x fewer transition samples to reach a satisfactory success rate, compared to the baseline. In a continual learning setup, SRSA efficiently learns policies for new tasks and incorporates them into the skill library, enhancing future policy learning. Furthermore, policies trained with SRSA in simulation achieve a 90% mean success rate when deployed in the real world. Please visit our project webpage https://srsa2024.github.io/.

Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning) of Large Language Models (LLMs) without human intervention. However, as our exploration deepens, it is crucial to critically assess whether these enhancements indeed signify comprehensive progress or if they could lead to unintended regressions. Through rigorous experimentation and analysis across diverse problem-solving tasks, we uncover nuances in the self-improvement trajectories of LLMs. Our study introduces the concept of \emph{self-improvement reversal}, where models showing improved overall accuracy metrics might paradoxically exhibit declines in broader, essential capabilities. We propose a comprehensive evaluative framework to scrutinize the underlying mechanisms and outcomes of post-training self-improvement, aiming to discern between superficial metric improvements and genuine enhancements in model functionality. The findings emphasize the complexity of technological advancements in LLMs, underscoring the need for a nuanced understanding of the \textit{progress or regress} dichotomy in their development.

Masked Generative Image Transformers (MaskGIT) have emerged as a scalable and efficient image generation framework, able to deliver high-quality visuals with low inference costs. However, MaskGIT’s token unmasking scheduler, an essential component of the framework, has not received the attention it deserves. We analyze the sampling objective in MaskGIT, based on the mutual information between tokens, and elucidate its shortcomings. We then propose a new sampling strategy based on our Halton scheduler instead of the original Confidence scheduler. More precisely, our method selects the token’s position according to a quasi-random, low-discrepancy Halton sequence. Intuitively, that method spreads the tokens spatially, progressively covering the image uniformly at each step. Our analysis shows that it allows reducing non-recoverable sampling errors, leading to simpler hyper-parameters tuning and better quality images. Our scheduler does not require retraining or noise injection and may serve as a simple drop-in replacement for the original sampling strategy. Evaluation of both class-to-image synthesis on ImageNet and text-to-image generation on the COCO dataset demonstrates that the Halton scheduler outperforms the Confidence scheduler quantitatively by reducing the FID and qualitatively by generating more diverse and more detailed images. Our code is at https://github.com/valeoai/Halton-MaskGIT.

Uncertainty quantification in time series prediction is challenging due to the temporal dependence and distribution shift on sequential data. Conformal prediction provides a pivotal and flexible instrument for assessing the uncertainty of machine learning models through prediction sets. Recently, a series of online conformal inference methods updated thresholds of prediction sets by performing online gradient descent on a sequence of quantile loss functions. A drawback of such methods is that they only use the information of revealed non-conformity scores via miscoverage indicators but ignore error quantification, namely the distance between the non-conformity score and the current threshold. To accurately leverage the dynamic of miscoverage error, we propose Error-quantified Conformal Inference (ECI) by smoothing the quantile loss function. ECI introduces a continuous and adaptive feedback scale with the miscoverage error, rather than simple binary feedback in existing methods. We establish a long-term coverage guarantee for ECI under arbitrary dependence and distribution shift. The extensive experimental results show that ECI can achieve valid miscoverage control and output tighter prediction sets than other baselines.

We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional black-box LLMs that rely on limited post-hoc interpretations, CB-LLMs integrate intrinsic interpretability directly into the LLMs -- allowing accurate explanations with scalability and transparency. We build CB-LLMs for two essential NLP tasks: text classification and text generation. In text classification, CB-LLMs is competitive with, and at times outperforms, traditional black-box models while providing explicit and interpretable reasoning. For the more challenging task of text generation, interpretable neurons in CB-LLMs enable precise concept detection, controlled generation, and safer outputs. The embedded interpretability empowers users to transparently identify harmful content, steer model behavior, and unlearn undesired concepts -- significantly enhancing the safety, reliability, and trustworthiness of LLMs, which are critical capabilities notably absent in existing language models.