Gibbs Sampling from Human Feedback: A Provable KL- constrained Framework for RLHF

This paper studies the theoretical framework of the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We consider a standard mathematical formulation, the reverse-KL regularized contextual bandit for RLHF. Despite its widespread practical application, a rigorous theoretical analysis of this formulation remains open. We investigate its theoretical properties both in offline and online settings and propose efficient algorithms with finite-sample theoretical guarantees. Our work bridges the gap between theory and practice by linking our theoretical insights with existing practical alignment algorithms such as Direct Preference Optimization (DPO) and Rejection Sampling Optimization (RSO). Furthermore, these findings and connections also offer both theoretical and practical communities new tools and insights for future algorithmic design of alignment algorithms.

Nova$^+$: Generative Language Models for Binaries

Generative large language models (LLMs) pre-trained on code have shown impressive effectiveness in code generation, program repair, and document analysis. However, existing generative LLMs focus on source code and are not specialized for binaries. There are three main challenges for LLMs to model and learn binary code: hex-decimal values, complex global dependencies, and compiler optimization levels. To bring the benefit of LLMs to the binary domain, we develop Nova and Nova$^+$, which are LLMs pre-trained on binary corpora. Nova is pre-trained with the standard language modeling task, showing significantly better capability on five benchmarks for three downstream tasks: binary code similarity detection (BCSD), binary code translation (BCT), and binary code recovery (BCR), over GPT-3.5 and other existing techniques. We build Nova$^+$ to further boost Nova using two new pre-training tasks, i.e., optimization generation and optimization level prediction, which are designed to learn binary optimization and align equivalent binaries. Nova$^+$ shows overall the best performance for all three downstream tasks on five benchmarks, demonstrating the contributions of the new pre-training tasks.

Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture

Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To address these challenges, we propose a novel framework for simultaneous high-fidelity recovery of object shapes and textures from single-view images. Our approach utilizes the proposed Single-view neural implicit Shape and Radiance field (SSR) representations to leverage both explicit 3D shape supervision and volume rendering of color, depth, and surface normal images. To overcome shape-appearance ambiguity under partial observations, we introduce a two-stage learning curriculum incorporating both 3D and 2D supervisions. A distinctive feature of our framework is its ability to generate fine-grained textured meshes while seamlessly integrating rendering capabilities into the single-view 3D reconstruction model. This integration enables not only improved textured 3D object reconstruction by 27.7% and 11.6% on the 3D-FRONT and Pix3D datasets, respectively, but also supports the rendering of images from novel viewpoints. Beyond individual objects, our approach facilitates composing object-level representations into flexible scene representations, thereby enabling applications such as holistic scene understanding and 3D scene editing. We conduct extensive experiments to demonstrate the effectiveness of our method.

Exploring the Relationship Between Model Architecture and In-Context Learning Ability

What is the relationship between model architecture and the ability to perform in-context learning? In this empirical study, we take the first steps towards answering this question. In particular, we evaluate fifteen model architectures across a suite of synthetic in-context learning tasks. The selected architectures represent a broad range of paradigms, including recurrent and convolution-based neural networks, transformers, and emerging attention alternatives. We discover that all considered architectures can perform in-context learning under certain conditions. However, contemporary architectures are found to be the best performing, especially as task complexity grows. Additionally, our follow-up experiments delve into various factors that influence in-context learning. We observe varied sensitivities among architectures with respect to hyperparameter settings. Our study of training dynamics reveals that certain architectures exhibit a smooth, progressive learning trajectory, while others demonstrate periods of stagnation followed by abrupt mastery of the task. Finally, and somewhat surprisingly, we find that several emerging attention alternatives are more robust in-context learners than transformers; since such approaches have constant-sized memory footprints at inference time, this result opens the future possibility of scaling up in-context learning to vastly larger numbers of in-context examples.

Solving Satisfiability Modulo Counting for Symbolic and Statistical AI Integration With Provable Guarantees

Satisfiability Modulo Counting (SMC) encompasses problems that require both symbolic decision-making and statistical reasoning. Its general formulation captures many real-world problems at the intersection of symbolic and statistical Artificial Intelligence. SMC searches for policy interventions to control probabilistic outcomes. Solving SMC is challenging because of its highly intractable nature($\text{NP}^{\text{PP}}$-complete), incorporating statistical inference and symbolic reasoning. Previous research on SMC solving lacks provable guarantees and/or suffers from sub-optimal empirical performance, especially when combinatorial constraints are present. We propose XOR-SMC, a polynomial algorithm with access to NP-oracles, to solve highly intractable SMC problems with constant approximation guarantees. XOR-SMC transforms the highly intractable SMC into satisfiability problems, by replacing the model counting in SMC with SAT formulae subject to randomized XOR constraints. Experiments on solving important SMC problems in AI for social good demonstrate that XOR-SMC finds solutions close to the true optimum, outperforming several baselines which struggle to find good approximations for the intractable model counting in SMC.

Racing Control Variable Genetic Programming for Symbolic Regression

Symbolic regression, as one of the most crucial tasks in AI for science, discovers governing equations from experimental data. Popular approaches based on genetic programming, Monte Carlo tree search, or deep reinforcement learning learn symbolic regression from a fixed dataset. They require massive datasets and long training time especially when learning complex equations involving many variables. Recently, Control Variable Genetic Programming (CVGP) has been introduced which accelerates the regression process by discovering equations from designed control variable experiments. However, the set of experiments is fixed a-priori in CVGP and we observe that sub-optimal selection of experiment schedules delay the discovery process significantly. To overcome this limitation, we propose Racing Control Variable Genetic Programming (Racing-CVGP), which carries out multiple experiment schedules simultaneously. A selection scheme similar to that used in selecting good symbolic equations in the genetic programming process is implemented to ensure that promising experiment schedules eventually win over the average ones. The unfavorable schedules are terminated early to save time for the promising ones. We evaluate Racing-CVGP on several synthetic and real-world datasets corresponding to true physics laws. We demonstrate that Racing-CVGP outperforms CVGP and a series of symbolic regressors which discover equations from fixed datasets.

Marginalized Importance Sampling for Off-Environment Policy Evaluation

Reinforcement Learning (RL) methods are typically sample-inefficient, making it challenging to train and deploy RL-policies in real world robots. Even a robust policy trained in simulation, requires a real-world deployment to assess their performance. This paper proposes a new approach to evaluate the real-world performance of agent policies without deploying them in the real world. The proposed approach incorporates a simulator along with real-world offline data to evaluate the performance of any policy using the framework of Marginalized Importance Sampling (MIS). Existing MIS methods face two challenges: (1) large density ratios that deviate from a reasonable range and (2) indirect supervision, where the ratio needs to be inferred indirectly, thus exacerbating estimation error. Our approach addresses these challenges by introducing the target policy's occupancy in the simulator as an intermediate variable and learning the density ratio as the product of two terms that can be learned separately. The first term is learned with direct supervision and the second term has a small magnitude, thus making it easier to run. We analyze the sample complexity as well as error propagation of our two step-procedure. Furthermore, we empirically evaluate our approach on Sim2Sim environments such as Cartpole, Reacher and Half-Cheetah. Our results show that our method generalizes well across a variety of Sim2Sim gap, target policies and offline data collection policies. We also demonstrate the performance of our algorithm on a Sim2Real task of validating the performance of a 7 DOF robotic arm using offline data along with a gazebo based arm simulator.

The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation

Theoretical guarantees in reinforcement learning (RL) are known to suffer multiplicative blow-up factors with respect to the misspecification error of function approximation. Yet, the nature of such \emph{approximation factors} -- especially their optimal form in a given learning problem -- is poorly understood. In this paper we study this question in linear off-policy value function estimation, where many open questions remain. We study the approximation factor in a broad spectrum of settings, such as with the weighted $L_2$-norm (where the weighting is the offline state distribution), the $L_\infty$ norm, the presence vs. absence of state aliasing, and full vs. partial coverage of the state space. We establish the optimal asymptotic approximation factors (up to constants) for all of these settings. In particular, our bounds identify two instance-dependent factors for the $L_2(\mu)$ norm and only one for the $L_\infty$ norm, which are shown to dictate the hardness of off-policy evaluation under misspecification.

Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise Approach

Accurately annotated ultrasonic images are vital components of a high-quality medical report. Hospitals often have strict guidelines on the types of annotations that should appear on imaging results. However, manually inspecting these images can be a cumbersome task. While a neural network could potentially automate the process, training such a model typically requires a dataset of paired input and target images, which in turn involves significant human labour. This study introduces an automated approach for detecting annotations in images. This is achieved by treating the annotations as noise, creating a self-supervised pretext task and using a model trained under the Noise2Noise scheme to restore the image to a clean state. We tested a variety of model structures on the denoising task against different types of annotation, including body marker annotation, radial line annotation, etc. Our results demonstrate that most models trained under the Noise2Noise scheme outperformed their counterparts trained with noisy-clean data pairs. The costumed U-Net yielded the most optimal outcome on the body marker annotation dataset, with high scores on segmentation precision and reconstruction similarity. We released our code at https://github.com/GrandArth/UltrasonicImage-N2N-Approach.

How Effective Are Neural Networks for Fixing Security Vulnerabilities

Security vulnerability repair is a difficult task that is in dire need of automation. Two groups of techniques have shown promise: (1) large code language models (LLMs) that have been pre-trained on source code for tasks such as code completion, and (2) automated program repair (APR) techniques that use deep learning (DL) models to automatically fix software bugs. This paper is the first to study and compare Java vulnerability repair capabilities of LLMs and DL-based APR models. The contributions include that we (1) apply and evaluate five LLMs (Codex, CodeGen, CodeT5, PLBART and InCoder), four fine-tuned LLMs, and four DL-based APR techniques on two real-world Java vulnerability benchmarks (Vul4J and VJBench), (2) design code transformations to address the training and test data overlapping threat to Codex, (3) create a new Java vulnerability repair benchmark VJBench, and its transformed version VJBench-trans and (4) evaluate LLMs and APR techniques on the transformed vulnerabilities in VJBench-trans. Our findings include that (1) existing LLMs and APR models fix very few Java vulnerabilities. Codex fixes 10.2 (20.4%), the most number of vulnerabilities. (2) Fine-tuning with general APR data improves LLMs' vulnerability-fixing capabilities. (3) Our new VJBench reveals that LLMs and APR models fail to fix many Common Weakness Enumeration (CWE) types, such as CWE-325 Missing cryptographic step and CWE-444 HTTP request smuggling. (4) Codex still fixes 8.3 transformed vulnerabilities, outperforming all the other LLMs and APR models on transformed vulnerabilities. The results call for innovations to enhance automated Java vulnerability repair such as creating larger vulnerability repair training data, tuning LLMs with such data, and applying code simplification transformation to facilitate vulnerability repair.