论文检索

Generative Models · Reasoning

SIJIA CHEN, Yibo Wang, Yi-Feng Wu, Qingguo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang

Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to improve their reasoning capabilities on complex tasks. This enables them to act as intelligent agents interacting with the real world. The recently introduced ToolLLaMA model by Qin et al. [2023] utilizes the depth-first search-based decision tree (DFSDT) mechanism for multi-step reasoning with $16000+$ real-world APIs, effectively enhancing the performance of tool-augmented LLMs compared to traditional chain reasoning mechanisms. However, their approach only employs successful paths from decision trees (also called inference trees) for supervised fine-tuning (SFT), missing out on the potential learning opportunities from failed paths. Inspired by this, we propose an inference trajectory optimization framework based on preference learning to address this limitation. We first introduce a novel method for constructing step-wise preference data from tree-like expert trajectories, which leverages the previously ignored failed explorations in the decision trees. In the subsequent training phase, we first fine-tune the LLM with successful tool-usage expert trajectories and then apply direct preference optimization (DPO) with the preference data to update the LLM's policy, resulting in our ToolPrefer-LLaMA (TP-LLaMA) model. This approach not only enhances the utilization of original expert data but also broadens the learning space of the model. Our experiments demonstrate that by obtaining insights from errors in inference trees, TP-LLaMA significantly outperforms the baselines across almost all test scenarios by a large margin and exhibits better generalization capabilities with unseen APIs. At the same time, TP-LLaMA has also demonstrated superior reasoning efficiency compared to the baselines, making it more suitable for complex tool-usage reasoning tasks.

Fairness

Zhen Zhang, Xiaohong Chen, Limei Liu, Jie Chen, Junyu Huang, Qilong Feng

Fair-range clustering extends classical clustering formulations by associating each data point with one or more demographic labels. It imposes lower and upper bound constraints on the number of facilities opened for each label, ensuring fair representation of all demographic groups by the selected facilities. In this paper we focus on the fair-range $k$-median and $k$-means problems in Euclidean spaces. We give $(1+\varepsilon)$-approximation algorithms with fixed-parameter tractable running times for both problems, parameterized by the numbers of opened facilities and demographic labels. For Euclidean metrics, these are the first parameterized approximation schemes for the problems, improving upon the previously known $O(1)$-approximation ratios given by Thejaswi et al. (KDD 2022).

Reinforcement Learning · Everything Else

Shen Li, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li, Julie A Shah

Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference strength. To address this, we leverage human response times, which are inversely related to preference strength, as an additional signal. We propose a computationally efficient method that combines choices and response times to estimate human utility functions, grounded in the EZ diffusion model from psychology. Theoretical and empirical analyses show that for queries with strong preferences, response times complement choices by providing extra information about preference strength, leading to significantly improved utility estimation. We incorporate this estimator into preference-based linear bandits for fixed-budget best-arm identification. Simulations on three real-world datasets demonstrate that using response times significantly accelerates preference learning compared to choice-only approaches. Additional materials, such as code, slides, and talk video, are available at https://shenlirobot.github.io/pages/NeurIPS24.html.

Reinforcement Learning · Everything Else

Shen Li, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li, Julie A Shah

Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference strength. To address this, we leverage human response times, which are inversely related to preference strength, as an additional signal. We propose a computationally efficient method that combines choices and response times to estimate human utility functions, grounded in the EZ diffusion model from psychology. Theoretical and empirical analyses show that for queries with strong preferences, response times complement choices by providing extra information about preference strength, leading to significantly improved utility estimation. We incorporate this estimator into preference-based linear bandits for fixed-budget best-arm identification. Simulations on three real-world datasets demonstrate that using response times significantly accelerates preference learning compared to choice-only approaches. Additional materials, such as code, slides, and talk video, are available at https://shenlirobot.github.io/pages/NeurIPS24.html.

Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas, Shujian Yu, Stjepan Picek

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and applicable to practical threat scenarios. State-of-the-art backdoor inversion recovers a mask in the feature space to locate prominent backdoor features, where benign and backdoor features can be disentangled. However, it suffers from high computational overhead, and we also find that it overly relies on prominent backdoor features that are highly distinguishable from benign features. To tackle these shortcomings, this paper improves backdoor feature inversion for backdoor detection by incorporating extra neuron activation information. In particular, we adversarially increase the loss of backdoored models with respect to weights to activate the backdoor effect, based on which we can easily differentiate backdoored and clean models. Experimental results demonstrate our defense, BAN, is 1.37$\times$ (on CIFAR-10) and 5.11$\times$ (on ImageNet200) more efficient with an average 9.99\% higher detect success rate than the state-of-the-art defense BTI DBF. Our code and trained models are publicly available at https://github.com/xiaoyunxxy/ban.

Learning Theory

Clément L Canonne, Qiping Yang

This paper studies the problem of \emph{entropy identity testing}: given sample access to a distribution $p$ and a fully described distribution $q$ (both are discrete distributions over the support of size $k$), and the promise that either $p = q$ or $ | H(p) - H(q) | \geqslant \varepsilon$, where $H(\cdot)$ denotes the Shannon entropy, a tester needs to distinguish between the two cases with high probability. We establish a near-optimal sample complexity bound of $\tilde{\Theta}(\sqrt{k}/\varepsilon + {1}/{\varepsilon^2}$) for this problem, and show how to apply it to the problem of identity testing for in-degree-$d$ $n$-dimensional Bayesian networks, obtaining an upper bound of $\tilde{O}( {2^{d / 2} n^{3/2}}/{\varepsilon^2} + {n^2}/{\varepsilon^4} )$. This improves on the sample complexity bound of $\tilde{O}(2^{d/2}n^2/\varepsilon^4)$ from Canonne, Diakonikolas, Kane, and Stewart (2020), which required an additional assumption on the structure of the (unknown) Bayesian network.

Theory · Active Learning and Interactive Learning

Nicolás Astorga, Tennison Liu, Nabeel Seedat, Mihaela van der Schaar

Conducting experiments and gathering data for machine learning models is a complex and expensive endeavor, particularly when confronted with limited information. Typically, extensive _experiments_ to obtain features and labels come with a significant acquisition cost, making it impractical to carry out all of them. Therefore, it becomes crucial to strategically determine what to acquire to maximize the predictive performance while minimizing costs. To perform this task, existing data acquisition methods assume the availability of an initial dataset that is both fully-observed and labeled, crucially overlooking the **partial observability** of features characteristic of many real-world scenarios. In response to this challenge, we present Partially Observable Cost-Aware Active-Learning (POCA), a new learning approach aimed at improving model generalization in data-scarce and data-costly scenarios through label and/or feature acquisition. Introducing $\mu$POCA as an instantiation, we maximise the uncertainty reduction in the predictive model when obtaining labels and features, considering associated costs. $\mu$POCA enhance traditional Active Learning metrics based solely on the observed features by generating the unobserved features through Generative Surrogate Models, particularly Large Language Models (LLMs). We empirically validate $\mu$POCA across diverse tabular datasets, varying data availability, acquisition costs, and LLMs.

Computer Vision

Wei Xu, Chunsheng Shi, Sifan Tu, Xin Zhou, Dingkang Liang, Xiang Bai

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are typically tailored to a specific task, limiting their understanding of 3D scenes to a task-specific perspective. In contrast, the proposed method unifies six tasks into unified representations processed by the same Transformer. It facilitates inter-task knowledge sharing, thereby promoting comprehensive 3D scene understanding. To take advantage of multi-task unification, we enhance performance by establishing explicit inter-task associations. Specifically, we design knowledge distillation and contrastive learning to transfer task-specific knowledge across different tasks. Experiments on three benchmarks, including ScanNet20, ScanRefer, and ScanNet200, demonstrate that the UniSeg3D consistently outperforms current SOTA methods, even those specialized for individual tasks. We hope UniSeg3D can serve as a solid unified baseline and inspire future work. Code and models are available at \url{https://dk-liang.github.io/UniSeg3D/}.

Yihao Zhang, Zeming Wei, Jun Sun, Meng Sun

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, developing practical and efficient methods for applying these representations for general and flexible model editing remains challenging. In this work, we explore how to leverage insights from representation engineering to guide the editing of LLMs by deploying a representation discriminator as an editing oracle. We first identify the importance of a robust and reliable discriminator during editing, then propose an \textbf{A}dversarial \textbf{R}epresentation \textbf{E}ngineering (\textbf{ARE}) framework to provide a unified and interpretable approach for conceptual model editing without compromising baseline performance. Experiments on multiple tasks demonstrate the effectiveness of ARE in various model editing scenarios. Our code and data are available at \url{https://github.com/Zhang-Yihao/Adversarial-Representation-Engineering}.

Reinforcement Learning · Deep RL

Qi Lv, Xiang Deng, Gongwei Chen, MICHAEL YU WANG, Liqiang Nie

While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions.Existing work attempts to address this issue by data augmentation with the learned policy or adding extra constraints with the value-based RL algorithm. However, these studies still fail to overcome the following challenges: (1) insufficiently utilizing the historical temporal information among inter-steps, (2) overlooking the local intra-step relationships among return-to-gos (RTGs), states, and actions, (3) overfitting suboptimal trajectories with noisy labels. To address these challenges, we propose $\textbf{D}$ecision $\textbf{M}$amba ($\textbf{DM}$), a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy.DM explicitly models the historical hidden state to extract the temporal information by using the mamba architecture. To capture the relationship among RTG-state-action triplets, a fine-grained SSM module is designed and integrated into the original coarse-grained SSM in mamba, resulting in a novel mamba architecture tailored for offline RL. Finally, to mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization. The policy evolves by using its own past knowledge to refine the suboptimal actions, thus enhancing its robustness on noisy demonstrations. Extensive experiments on various tasks show that DM outperforms other baselines substantially.

Optimization · Optimization and Learning under Uncertainty

Qiang LI, Hoi-To Wai

This paper studies a risk minimization problem with decision dependent data distribution. The problem pertains to the performative prediction setting in which a trained model can affect the outcome estimated by the model. Such dependency creates a feedback loop that influences the stability of optimization algorithms such as stochastic gradient descent (SGD). We present the first study on performative prediction with smooth but possibly non-convex loss. We analyze a greedy deployment scheme with SGD (SGD-GD). Note that in the literature, SGD-GD is often studied with strongly convex loss. We first propose the definition of stationary performative stable (SPS) solutions through relaxing the popular performative stable condition. We then prove that SGD-GD converges to a biased SPS solution in expectation. We consider two conditions of sensitivity on the distribution shifts: (i) the sensitivity is characterized by Wasserstein-1 distance and the loss is Lipschitz w.r.t.~data samples, or (ii) the sensitivity is characterized by total variation (TV) divergence and the loss is bounded. In both conditions, the bias levels are proportional to the stochastic gradient's variance and sensitivity level. Our analysis is extended to a lazy deployment scheme where models are deployed once per several SGD updates, and we show that it converges to an SPS solution with reduced bias. Numerical experiments corroborate our theories.

Ruihan Gao, Kangle Deng, Gengshan Yang, Wenzhen Yuan, Jun-Yan Zhu

3D generation methods have shown visually compelling results powered by diffusion image priors. However, they often fail to produce realistic geometric details, resulting in overly smooth surfaces or geometric details inaccurately baked in albedo maps. To address this, we introduce a new method that incorporates touch as an additional modality to improve the geometric details of generated 3D assets. We design a lightweight 3D texture field to synthesize visual and tactile textures, guided by 2D diffusion model priors on both visual and tactile domains. We condition the visual texture generation on high-resolution tactile normals and guide the patch-based tactile texture refinement with a customized TextureDreambooth. We further present a multi-part generation pipeline that enables us to synthesize different textures across various regions. To our knowledge, we are the first to leverage high-resolution tactile sensing to enhance geometric details for 3D generation tasks. We evaluate our method in both text-to-3D and image-to-3D settings. Our experiments demonstrate that our method provides customized and realistic fine geometric textures while maintaining accurate alignment between two modalities of vision and touch.

Neuroscience, Cognitive Science

Roy Abel, Shimon Ullman

As part of the effort to understand how the brain learns, ongoing research seeks to combine biological knowledge with current artificial intelligence (AI) modeling in an attempt to find an efficient biologically plausible learning scheme. Current models often use a cortical-like combination of bottom-up (BU) and top-down (TD) processing, where the TD part carries feedback signals for learning. However, in the visual cortex, the TD pathway plays a second major role in visual attention, by guiding the visual process toward locations and tasks of interest. A biological model should therefore integrate both learning and visual guidance. We introduce a model that uses a cortical-like combination of BU and TD processing that naturally integrates the two major functions of the TD stream. This integration is achieved through an appropriate connectivity pattern between the BU and TD streams, a novel processing cycle that uses the TD stream twice, and a 'Counter-Hebb' learning mechanism that operates across both streams. We show that the 'Counter-Hebb' mechanism can provide an exact backpropagation synaptic modification. Additionally, our model can effectively guide the visual stream to perform a task of interest, achieving competitive performance on standard multi-task learning benchmarks compared to AI models. The successful combination of learning and visual guidance could provide a new view on combining BU and TD processing in human vision and suggests possible directions for both biologically plausible models and artificial instructed models, such as vision-language models (VLMs).

Deep Learning · Attention Mechanisms

Fernando Moreno-Pino, Alvaro Arroyo, Harrison Waldon, Xiaowen Dong, Alvaro Cartea

Time-series data in real-world settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In these settings, traditional sequence-based recurrent models struggle. To overcome this, researchers often replace recurrent models with Neural ODE-based architectures to account for irregularly sampled data and use Transformer-based architectures to account for long-range dependencies. Despite the success of these two approaches, both incur very high computational costs for input sequences of even moderate length. To address this challenge, we introduce the Rough Transformer, a variation of the Transformer model that operates on continuous-time representations of input sequences and incurs significantly lower computational costs. In particular, we propose multi-view signature attention, which uses path signatures to augment vanilla attention and to capture both local and global (multi-scale) dependencies in the input data, while remaining robust to changes in the sequence length and sampling frequency and yielding improved spatial processing. We find that, on a variety of time-series-related tasks, Rough Transformers consistently outperform their vanilla attention counterparts while obtaining the representational benefits of Neural ODE-based models, all at a fraction of the computational time and memory resources.

Deep Learning · Algorithms

Xavier Gonzalez, Andrew Warrington, Jimmy Smith, Scott Linderman

Transformers and linear state space models can be evaluated in parallel on modern hardware, but evaluating nonlinear RNNs appears to be an inherently sequential problem. Recently, however, Lim et al. '24 developed an approach called DEER, which evaluates nonlinear RNNs in parallel by posing the states as the solution to a fixed-point problem. They derived a parallel form of Newton's method to solve the fixed-point problem and achieved significant speedups over sequential evaluation. However, the computational complexity of DEER is cubic in the state size, and the algorithm can suffer from numerical instability. We address these limitations with two novel contributions. To reduce the computational complexity, we apply quasi-Newton approximations and show they converge comparably to Newton, use less memory, and are faster. To stabilize DEER, we leverage a connection between the Levenberg-Marquardt algorithm and Kalman smoothing, which we call ELK. This connection allows us to stabilize Newton's method while using efficient parallelized Kalman smoothing algorithms to retain performance. Through several experiments, we show that these innovations allow for parallel evaluation of nonlinear RNNs at larger scales and with greater stability.

Fairness

Cong Zeng, Shengkun Tang, Xianjun Yang, Yuanzhou Chen, Yiyou Sun, Zhiqiang Xu, Yao Li, Haifeng Chen, Wei Cheng, Dongkuan (DK) Xu

The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in distinguishing one from the other – a task further complicated by the frequent updates and closed nature of leading proprietary LLMs. Traditional logits-based detection methods leverage surrogate models for identifying LLM-generated content when the exact logits are unavailable from black-box LLMs. However, these methods grapple with the misalignment between the distributions of the surrogate and the often undisclosed target models, leading to performance degradation, particularly with the introduction of new, closed-source models. Furthermore, while current methodologies are generally effective when the source model is identified, they falter in scenarios where the model version remains unknown, or the test set comprises outputs from various source models. To address these limitations, we present \textbf{D}istribution-\textbf{A}ligned \textbf{L}LMs \textbf{D}etection (DALD), an innovative framework that redefines the state-of-the-art performance in black-box text detection even without logits from source LLMs. DALD is designed to align the surrogate model's distribution with that of unknown target LLMs, ensuring enhanced detection capability and resilience against rapid model iterations with minimal training investment. By leveraging corpus samples from publicly accessible outputs of advanced models such as ChatGPT, GPT-4 and Claude-3, DALD fine-tunes surrogate models to synchronize with unknown source model distributions effectively. Our approach achieves SOTA performance in black-box settings on different advanced closed-source and open-source models. The versatility of our method enriches widely adopted zero-shot detection frameworks (DetectGPT, DNA-GPT, Fast-DetectGPT) with a `plug-and-play' enhancement feature. Extensive experiments validate that our methodology reliably secures high detection precision for LLM-generated text and effectively detects text from diverse model origins through a singular detector.Our method is also robust under the revised text attack and non-English texts.

Reinforcement Learning · Planning

Daniel Bramblett, Siddharth Srivastava

Planning in real-world settings often entails addressing partial observability while aligning with users' requirements. We present a novel framework for expressing users' constraints and preferences about agent behavior in a partially observable setting using parameterized belief-state query (BSQ) policies in the setting of goal-oriented partially observable Markov decision processes (gPOMDPs). We present the first formal analysis of such constraints and prove that while the expected cost function of a parameterized BSQ policy w.r.t its parameters is not convex, it is piecewise constant and yields an implicit discrete parameter search space that is finite for finite horizons. This theoretical result leads to novel algorithms that optimize gPOMDP agent behavior with guaranteed user alignment. Analysis proves that our algorithms converge to the optimal user-aligned behavior in the limit. Empirical results show that parameterized BSQ policies provide a computationally feasible approach for user-aligned planning in partially observable settings.

Deep Learning · Everything Else

Shikuang Deng, Yuhang Wu, KANGRUI DU, Shi Gu

Spiking neural networks (SNNs), inspired by biological processes, use spike signals for inter-layer communication, presenting an energy-efficient alternative to traditional neural networks. To realize the theoretical advantages of SNNs in energy efficiency, it is essential to deploy them onto neuromorphic chips. On clock-driven synchronous chips, employing shorter time steps can enhance energy efficiency but reduce SNN performance. Compared to the clock-driven synchronous chip, the event-driven asynchronous chip achieves much lower energy consumption but only supports some specific network operations. Recently, a series of SNN projects have achieved tremendous success, significantly improving the SNN's performance. However, event-driven asynchronous chips do not support some of the proposed structures, making it impossible to integrate these SNNs into asynchronous hardware. In response to these problems, we propose the Spiking Token Mixer (STMixer) architecture, which consists exclusively of operations supported by asynchronous scenarios, including convolutional, fully connected layers and residual paths. Our series of experiments also demonstrates that STMixer achieves performance on par with spiking transformers in synchronous scenarios with very low timesteps. This indicates its ability to achieve the same level of performance with lower power consumption in synchronous scenarios. The codes are available at \url{https://github.com/brain-intelligence-lab/STMixer_demo}.

Computer Vision

Yoonki Cho, Jaeyoon Kim, Woo Jae Kim, Junsik Jung, Sung-eui Yoon

Domain generalizable person re-identification (DG re-ID) aims to learn discriminative representations that are robust to distributional shifts. While data augmentation is a straightforward solution to improve generalization, certain augmentations exhibit a polarized effect in this task, enhancing in-distribution performance while deteriorating out-of-distribution performance. In this paper, we investigate this phenomenon and reveal that it leads to sparse representation spaces with reduced uniformity. To address this issue, we propose a novel framework, Balancing Alignment and Uniformity (BAU), which effectively mitigates this effect by maintaining a balance between alignment and uniformity. Specifically, BAU incorporates alignment and uniformity losses applied to both original and augmented images and integrates a weighting strategy to assess the reliability of augmented samples, further improving the alignment loss. Additionally, we introduce a domain-specific uniformity loss that promotes uniformity within each source domain, thereby enhancing the learning of domain-invariant features. Extensive experimental results demonstrate that BAU effectively exploits the advantages of data augmentation, which previous studies could not fully utilize, and achieves state-of-the-art performance without requiring complex training procedures. The code is available at https://github.com/yoonkicho/BAU.

Language · Factuality

Yasin Abbasi Yadkori, Ilja Kuzborskij, András György, Csaba Szepesvari

We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider both epistemic and aleatoric uncertainties, where the former comes from the lack of knowledge about the ground truth (such as about facts or the language), and the latter comes from irreducible randomness (such as multiple possible answers). In particular, we derive an information-theoretic metric that allows to reliably detect when only epistemic uncertainty is large, in which case the output of the model is unreliable. This condition can be computed based solely on the output of the model obtained simply by some special iterative prompting based on the previous responses. Such quantification, for instance, allows to detect hallucinations (cases when epistemic uncertainty is high) in both single- and multi-answer responses. This is in contrast to many standard uncertainty quantification strategies (such as thresholding the log-likelihood of a response) where hallucinations in the multi-answer case cannot be detected. We conduct a series of experiments which demonstrate the advantage of our formulation. Further, our investigations shed some light on how the probabilities assigned to a given output by an LLM can be amplified by iterative prompting, which might be of independent interest.