Add to Chrome
Add to Firefox
Add to EdgeThe Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
May 28, 2025
This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy dropped sharply at the early training stage, this diminished exploratory ability is always accompanied with the saturation of policy performance. In practice, we establish a transformation equation R=-a*e^H+b between entropy H and downstream performance R. This empirical law strongly indicates that, the policy performance is traded from policy entropy, thus bottlenecked by its exhaustion, and the ceiling is fully predictable H=0, R=-a+b. Our finding necessitates entropy management for continuous exploration toward scaling compute for RL. To this end, we investigate entropy dynamics both theoretically and empirically. Our derivation highlights that, the change in policy entropy is driven by the covariance between action probability and the change in logits, which is proportional to its advantage when using Policy Gradient-like algorithms. Empirical study shows that, the values of covariance term and entropy differences matched exactly, supporting the theoretical conclusion. Moreover, the covariance term stays mostly positive throughout training, further explaining why policy entropy would decrease monotonically. Through understanding the mechanism behind entropy dynamics, we motivate to control entropy by restricting the update of high-covariance tokens. Specifically, we propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively. Experiments show that these methods encourage exploration, thus helping policy escape entropy collapse and achieve better downstream performance.
Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous Driving
May 20, 2025Autonomous Driving (AD) systems demand the high levels of safety assurance. Despite significant advancements in AD demonstrated on open-source benchmarks like Longest6 and Bench2Drive, existing datasets still lack regulatory-compliant scenario libraries for closed-loop testing to comprehensively evaluate the functional safety of AD. Meanwhile, real-world AD accidents are underrepresented in current driving datasets. This scarcity leads to inadequate evaluation of AD performance, posing risks to safety validation and practical deployment. To address these challenges, we propose Safety2Drive, a safety-critical scenario library designed to evaluate AD systems. Safety2Drive offers three key contributions. (1) Safety2Drive comprehensively covers the test items required by standard regulations and contains 70 AD function test items. (2) Safety2Drive supports the safety-critical scenario generalization. It has the ability to inject safety threats such as natural environment corruptions and adversarial attacks cross camera and LiDAR sensors. (3) Safety2Drive supports multi-dimensional evaluation. In addition to the evaluation of AD systems, it also supports the evaluation of various perception tasks, such as object detection and lane detection. Safety2Drive provides a paradigm from scenario construction to validation, establishing a standardized test framework for the safe deployment of AD.
Feedback-Free Resource Scheduling: Towards Flexible Multi-BS Cooperation in FD-RAN
Feb 25, 2025Flexible cooperation among base stations (BSs) is critical to improve resource utilization efficiency and meet personalized user demands. However, its practical implementation is hindered by the current radio access network (RAN), which relies on the coupling of uplink and downlink transmissions and channel state information feedback with inherent issues such as overheads and delays. To overcome these limitations, we consider the fully-decoupled RAN (FD-RAN), in which uplink and downlink networks are independent, and feedback-free MIMO transmission is adopted at the physical layer. To further deliver flexible cooperation in FD-RAN, we investigate the practical scheduling process and study feedback-free downlink multi-BS resource scheduling. The problem is considered based on network load conditions. In heavy-load states where it is impossible for all user demands to be met, an optimal greedy algorithm is proposed, maximizing the weighted sum of user demand satisfaction rates. In light-load states where at least one solution exists to satisfy all user demands, an optimal two-stage resource allocation algorithm is designed to further minimize network energy consumption by leveraging the flexibility of cooperation. Extensive simulations validate the superiority of proposed algorithms in performance and running time, and highlight the potential for realizing flexible cooperation in practice.
ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning
Dec 10, 2024Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of various optimization sub-modules to generate diverse EAs during training. Additionally, we propose a Transformer-based neural network to meta-learn a universal configuration policy through multitask reinforcement learning across a designed joint optimization task space. Extensive experiments verify that, our ConfigX, after large-scale pre-training, achieves robust zero-shot generalization to unseen tasks and outperforms state-of-the-art baselines. Moreover, ConfigX exhibits strong lifelong learning capabilities, allowing efficient adaptation to new tasks through fine-tuning. Our proposed ConfigX represents a significant step toward an automatic, all-purpose configuration agent for EAs.
Reciprocal Point Learning Network with Large Electromagnetic Kernel for SAR Open-Set Recognition
Nov 07, 2024The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones as "unknown." The chief challenge in OSR involves concurrently mitigating risks associated with generalizing features from a restricted set of known classes to numerous unknown samples and the open space exposure to potential unknown data. To enhance open-set SAR classification, a method called scattering kernel with reciprocal learning network is proposed. Initially, a feature learning framework is constructed based on reciprocal point learning (RPL), establishing a bounded space for potential unknown classes. This approach indirectly introduces unknown information into a learner confined to known classes, thereby acquiring more concise and discriminative representations. Subsequently, considering the variability in the imaging of targets at different angles and the discreteness of components in SAR images, a proposal is made to design convolutional kernels based on large-sized attribute scattering center models. This enhances the ability to extract intrinsic non-linear features and specific scattering characteristics in SAR images, thereby improving the discriminative features of the model and mitigating the impact of imaging variations on classification performance. Experiments on the MSTAR datasets substantiate the superior performance of the proposed approach called ASC-RPL over mainstream methods.
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
Oct 14, 2024
We present MEGA-Bench, an evaluation suite that scales multimodal evaluation to over 500 real-world tasks, to address the highly heterogeneous daily use cases of end users. Our objective is to optimize for a set of high-quality data samples that cover a highly diverse and rich set of multimodal tasks, while enabling cost-effective and accurate model evaluation. In particular, we collected 505 realistic tasks encompassing over 8,000 samples from 16 expert annotators to extensively cover the multimodal task space. Instead of unifying these problems into standard multi-choice questions (like MMMU, MMBench, and MMT-Bench), we embrace a wide range of output formats like numbers, phrases, code, \LaTeX, coordinates, JSON, free-form, etc. To accommodate these formats, we developed over 40 metrics to evaluate these tasks. Unlike existing benchmarks, MEGA-Bench offers a fine-grained capability report across multiple dimensions (e.g., application, input type, output format, skill), allowing users to interact with and visualize model capabilities in depth. We evaluate a wide variety of frontier vision-language models on MEGA-Bench to understand their capabilities across these dimensions.
Neural Exploratory Landscape Analysis
Aug 20, 2024
Recent research in Meta-Black-Box Optimization (MetaBBO) have shown that meta-trained neural networks can effectively guide the design of black-box optimizers, significantly reducing the need for expert tuning and delivering robust performance across complex problem distributions. Despite their success, a paradox remains: MetaBBO still rely on human-crafted Exploratory Landscape Analysis features to inform the meta-level agent about the low-level optimization progress. To address the gap, this paper proposes Neural Exploratory Landscape Analysis (NeurELA), a novel framework that dynamically profiles landscape features through a two-stage, attention-based neural network, executed in an entirely end-to-end fashion. NeurELA is pre-trained over a variety of MetaBBO algorithms using a multi-task neuroevolution strategy. Extensive experiments show that NeurELA achieves consistently superior performance when integrated into different and even unseen MetaBBO tasks and can be efficiently fine-tuned for further performance boost. This advancement marks a pivotal step in making MetaBBO algorithms more autonomous and broadly applicable.
PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify
Jun 01, 2024This paper proposes a novel "auto-agglomerative" 3D fracture assembly method, PuzzleFusion++, resembling how humans solve challenging spatial puzzles. Starting from individual fragments, the approach 1) aligns and merges fragments into larger groups akin to agglomerative clustering and 2) repeats the process iteratively in completing the assembly akin to auto-regressive methods. Concretely, a diffusion model denoises the 6-DoF alignment parameters of the fragments simultaneously, and a transformer model verifies and merges pairwise alignments into larger ones, whose process repeats iteratively. Extensive experiments on the Breaking Bad dataset show that PuzzleFusion++ outperforms all other state-of-the-art techniques by significant margins across all metrics, in particular by over 10% in part accuracy and 50% in Chamfer distance. The code will be available on our project page: https://puzzlefusion-plusplus.github.io.
Performance Analysis of Uplink/Downlink Decoupled Access in Cellular-V2X Networks
May 10, 2024This paper firstly develops an analytical framework to investigate the performance of uplink (UL) / downlink (DL) decoupled access in cellular vehicle-to-everything (C-V2X) networks, in which a vehicle's UL/DL can be connected to different macro/small base stations (MBSs/SBSs) separately. Using the stochastic geometry analytical tool, the UL/DL decoupled access C-V2X is modeled as a Cox process, and we obtain the following theoretical results, i.e., 1) the probability of different UL/DL joint association cases i.e., both the UL and DL are associated with the different MBSs or SBSs, or they are associated with different types of BSs; 2) the distance distribution of a vehicle to its serving BSs in each case; 3) the spectral efficiency of UL/DL in each case; and 4) the UL/DL coverage probability of MBS/SBS. The analyses reveal the insights and performance gain of UL/DL decoupled access. Through extensive simulations, \textcolor{black}{the accuracy of the proposed analytical framework is validated.} Both the analytical and simulation results show that UL/DL decoupled access can improve spectral efficiency. The theoretical results can be directly used for estimating the statistical performance of a UL/DL decoupled access C-V2X network.
* 15 pages, 10 figures
Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning
Apr 12, 2024
Evolutionary computation (EC) algorithms, renowned as powerful black-box optimizers, leverage a group of individuals to cooperatively search for the optimum. The exploration-exploitation tradeoff (EET) plays a crucial role in EC, which, however, has traditionally been governed by manually designed rules. In this paper, we propose a deep reinforcement learning-based framework that autonomously configures and adapts the EET throughout the EC search process. The framework allows different individuals of the population to selectively attend to the global and local exemplars based on the current search state, maximizing the cooperative search outcome. Our proposed framework is characterized by its simplicity, effectiveness, and generalizability, with the potential to enhance numerous existing EC algorithms. To validate its capabilities, we apply our framework to several representative EC algorithms and conduct extensive experiments on the augmented CEC2021 benchmark. The results demonstrate significant improvements in the performance of the backbone algorithms, as well as favorable generalization across diverse problem classes, dimensions, and population sizes. Additionally, we provide an in-depth analysis of the EET issue by interpreting the learned behaviors of EC.