arXiv subjects

Songyang Zhang

Publications and source records attributed to Songyang Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's parameters, we identify parallels between LLM reasoning and various meta-learning paradigms. We formalize the training process for reasoning tasks as a meta-learning setup, with each question treated as an individual task, and reasoning trajectories serving as the inner loop optimization for adapting model parameters. Once trained on a diverse set of questions, the LLM develops fundamental reasoning capabilities that can generalize to previously unseen questions. Extensive empirical evaluations substantiate the strong connection between LLM reasoning and meta-learning, exploring several issues of significant interest from a meta-learning standpoint. Our work not only enhances the understanding of LLM reasoning but also provides practical insights for improving these models through established meta-learning techniques.

cs.CL↗

arXiv2025

Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering

We introduce KoLasSimpleQA, the first benchmark evaluating the multilingual factual ability of Large Language Models (LLMs). Inspired by existing research, we created the question set with features such as single knowledge point coverage, absolute objectivity, unique answers, and temporal stability. These questions enable efficient evaluation using the LLM-as-judge paradigm, testing both the LLMs' factual memory and self-awareness ("know what they don't know"). KoLasSimpleQA expands existing research in two key dimensions: (1) Breadth (Multilingual Coverage): It includes 9 languages, supporting global applicability evaluation. (2) Depth (Dual Domain Design): It covers both the general domain (global facts) and the language-specific domain (such as history, culture, and regional traditions) for a comprehensive assessment of multilingual capabilities. We evaluated mainstream LLMs, including traditional LLM and emerging Large Reasoning Models. Results show significant performance differences between the two domains, particularly in performance metrics, ranking, calibration, and robustness. This highlights the need for targeted evaluation and optimization in multilingual contexts. We hope KoLasSimpleQA will help the research community better identify LLM capability boundaries in multilingual contexts and provide guidance for model optimization. We will release KoLasSimpleQA at https://github.com/opendatalab/KoLasSimpleQA .

cs.CL↗

arXiv2025

TACO: Rethinking Semantic Communications with Task Adaptation and Context Embedding

Recent advancements in generative artificial intelligence have introduced groundbreaking approaches to innovating next-generation semantic communication, which prioritizes conveying the meaning of a message rather than merely transmitting raw data. A fundamental challenge in semantic communication lies in accurately identifying and extracting the most critical semantic information while adapting to downstream tasks without degrading performance, particularly when the objective at the receiver may evolve over time. To enable flexible adaptation to multiple tasks at the receiver, this work introduces a novel semantic communication framework, which is capable of jointly capturing task-specific information to enhance downstream task performance and contextual information. Through rigorous experiments on popular image datasets and computer vision tasks, our framework shows promising improvement compared to existing work, including superior performance in downstream tasks, better generalizability, ultra-high bandwidth efficiency, and low reconstruction latency.

cs.AI↗

arXiv2025

Task-Adaptive Semantic Communications with Controllable Diffusion-based Data Regeneration

Semantic communications represent a new paradigm of next-generation networking that shifts bit-wise data delivery to conveying the semantic meanings for bandwidth efficiency. To effectively accommodate various potential downstream tasks at the receiver side, one should adaptively convey the most critical semantic information. This work presents a novel task-adaptive semantic communication framework based on diffusion models that is capable of dynamically adjusting the semantic message delivery according to various downstream tasks. Specifically, we initialize the transmission of a deep-compressed general semantic representation from the transmitter to enable diffusion-based coarse data reconstruction at the receiver. The receiver identifies the task-specific demands and generates textual prompts as feedback. Integrated with the attention mechanism, the transmitter updates the semantic transmission with more details to better align with the objectives of the intended receivers. Our test results demonstrate the efficacy of the proposed method in adaptively preserving critical task-relevant information for semantic communications while preserving high compression efficiency.

cs.CL↗

arXiv2025

Mixture-of-Experts for Distributed Edge Computing with Channel-Aware Gating Function

In a distributed mixture-of-experts (MoE) system, a server collaborates with multiple specialized expert clients to perform inference. The server extracts features from input data and dynamically selects experts based on their areas of specialization to produce the final output. Although MoE models are widely valued for their flexibility and performance benefits, adapting distributed MoEs to operate effectively in wireless networks has remained unexplored. In this work, we introduce a novel channel-aware gating function for wireless distributed MoE, which incorporates channel conditions into the MoE gating mechanism. To train the channel-aware gating, we simulate various signal-to-noise ratios (SNRs) for each expert's communication channel and add noise to the features distributed to the experts based on these SNRs. The gating function then utilizes both features and SNRs to optimize expert selection. Unlike conventional MoE models which solely consider the alignment of features with the specializations of experts, our approach additionally considers the impact of channel conditions on expert performance. Experimental results demonstrate that the proposed channel-aware gating scheme outperforms traditional MoE models.

cs.LG↗

arXiv2025

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

Recent evaluations of Large Multimodal Models (LMMs) have explored their capabilities in various domains, with only few benchmarks specifically focusing on urban environments. Moreover, existing urban benchmarks have been limited to evaluating LMMs with basic region-level urban tasks under singular views, leading to incomplete evaluations of LMMs' abilities in urban environments. To address these issues, we present UrBench, a comprehensive benchmark designed for evaluating LMMs in complex multi-view urban scenarios. UrBench contains 11.6K meticulously curated questions at both region-level and role-level that cover 4 task dimensions: Geo-Localization, Scene Reasoning, Scene Understanding, and Object Understanding, totaling 14 task types. In constructing UrBench, we utilize data from existing datasets and additionally collect data from 11 cities, creating new annotations using a cross-view detection-matching method. With these images and annotations, we then integrate LMM-based, rule-based, and human-based methods to construct large-scale high-quality questions. Our evaluations on 21 LMMs show that current LMMs struggle in the urban environments in several aspects. Even the best performing GPT-4o lags behind humans in most tasks, ranging from simple tasks such as counting to complex tasks such as orientation, localization and object attribute recognition, with an average performance gap of 17.4%. Our benchmark also reveals that LMMs exhibit inconsistent behaviors with different urban views, especially with respect to understanding cross-view relations.

cs.CV↗

arXiv2025

Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications

Semantic communication marks a new paradigm shift from bit-wise data transmission to semantic information delivery for the purpose of bandwidth reduction. To more effectively carry out specialized downstream tasks at the receiver end, it is crucial to define the most critical semantic message in the data based on the task or goal-oriented features. In this work, we propose a novel goal-oriented communication (GO-COM) framework, namely Goal-Oriented Semantic Variational Autoencoder (GOS-VAE), by focusing on the extraction of the semantics vital to the downstream tasks. Specifically, we adopt a Vector Quantized Variational Autoencoder (VQ-VAE) to compress media data at the transmitter side. Instead of targeting the pixel-wise image data reconstruction, we measure the quality-of-service at the receiver end based on a pre-defined task-incentivized model. Moreover, to capture the relevant semantic features in the data reconstruction, imitation learning is adopted to measure the data regeneration quality in terms of goal-oriented semantics. Our experimental results demonstrate the power of imitation learning in characterizing goal-oriented semantics and bandwidth efficiency of our proposed GOS-VAE.

cs.LG↗

arXiv2025

TiRE-GAN: Task-Incentivized Generative Learning for Radiomap Estimation

To characterize radio frequency (RF) signal power distribution in wireless communication systems, the radiomap is a useful tool for resource allocation and network management. Usually, a dense radiomap is reconstructed from sparse observations collected by deployed sensors or mobile devices. To leverage both physical principles of radio propagation models and data statistics from sparse observations, this work introduces a novel task-incentivized generative learning model, namely TiRE-GAN, for radiomap estimation. Specifically, we first introduce a radio depth map to capture the overall pattern of radio propagation and shadowing effects, following which a task-driven incentive network is proposed to provide feedback for radiomap compensation depending on downstream tasks. Our experimental results demonstrate the power of the radio depth map to capture radio propagation information, and the efficiency of the proposed TiRE-GAN for radiomap estimation.

eess.SP↗

arXiv2025

Efficient Transmission of Radiomaps via Physics-Enhanced Semantic Communications

Enriching information of spectrum coverage, radiomap plays an important role in many wireless communication applications, such as resource allocation and network optimization. To enable real-time, distributed spectrum management, particularly in the scenarios with unstable and dynamic environments, the efficient transmission of spectrum coverage information for radiomaps from edge devices to the central server emerges as a critical problem. In this work, we propose an innovative physics-enhanced semantic communication framework tailored for efficient radiomap transmission based on generative learning models. Specifically, instead of bit-wise message passing, we only transmit the key "semantics" in radiomaps characterized by the radio propagation behavior and surrounding environments, where semantic compression schemes are utilized to reduce the communication overhead. Incorporating the novel concepts of Radio Depth Maps, the radiomaps are reconstructed from the delivered semantic information backboned on the conditional generative adversarial networks. Our framework is further extended to facilitate its implementation in the scenarios of multi-user edge computing, by integrating with federated learning for collaborative model training while preserving the data privacy. Experimental results show that our approach achieves high accuracy in radio coverage information recovery at ultra-high bandwidth efficiency, which has great potentials in many wireless-generated data transmission applications.

eess.SP↗

arXiv2025

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks. However, the complete technical details remain unrevealed, and the techniques that are believed certainly to be adopted are only reinforcement learning (RL) and the long chain of thoughts. This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through \textbf{O}utcome \textbf{RE}w\textbf{A}rd-based reinforcement \textbf{L}earning for mathematical reasoning tasks, where only binary outcome rewards are easily accessible. We theoretically prove that behavior cloning on positive trajectories from best-of-N (BoN) sampling is sufficient to learn the KL-regularized optimal policy in binary feedback environments. This formulation further implies that the rewards of negative samples should be reshaped to ensure the gradient consistency between positive and negative samples. To alleviate the long-existing difficulties brought by sparse rewards in RL, which are even exacerbated by the partial correctness of the long chain of thought for reasoning tasks, we further apply a token-level reward model to sample important tokens in reasoning trajectories for learning. With OREAL, for the first time, a 7B model can obtain 94.0 pass@1 accuracy on MATH-500 through RL, being on par with 32B models. OREAL-32B also surpasses previous 32B models trained by distillation with 95.0 pass@1 accuracy on MATH-500. Our investigation also indicates the importance of initial policy models and training queries for RL. Code, models, and data will be released to benefit future research\footnote{https://github.com/InternLM/OREAL}.

cs.CL↗

arXiv2025

Physics-Inspired Distributed Radio Map Estimation

To gain panoramic awareness of spectrum coverage in complex wireless environments, data-driven learning approaches have recently been introduced for radio map estimation (RME). While existing deep learning based methods conduct RME given spectrum measurements gathered from dispersed sensors in the region of interest, they rely on centralized data at a fusion center, which however raises critical concerns on data privacy leakages and high communication overloads. Federated learning (FL) enhance data security and communication efficiency in RME by allowing multiple clients to collaborate in model training without directly sharing local data. However, the performance of the FL-based RME can be hindered by the problem of task heterogeneity across clients due to their unavailable or inaccurate landscaping information. To fill this gap, in this paper, we propose a physics-inspired distributed RME solution in the absence of landscaping information. The main idea is to develop a novel distributed RME framework empowered by leveraging the domain knowledge of radio propagation models, and by designing a new distributed learning approach that splits the entire RME model into two modules. A global autoencoder module is shared among clients to capture the common pathloss influence on radio propagation pattern, while a client-specific autoencoder module focuses on learning the individual features produced by local shadowing effects from the unique building distributions in local environment. Simulation results show that our proposed method outperforms the benchmarks in achieving higher performance.

cs.LG↗

arXiv2025

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement

The quality of Supervised Fine-Tuning (SFT) data plays a critical role in enhancing the conversational capabilities of Large Language Models (LLMs). However, as LLMs become more advanced, the availability of high-quality human-annotated SFT data has become a significant bottleneck, necessitating a greater reliance on synthetic training data. In this work, we introduce Condor, a novel two-stage synthetic data generation framework that incorporates World Knowledge Tree and Self-Reflection Refinement to produce high-quality SFT data at scale. Our experimental results demonstrate that a base model fine-tuned on only 20K Condor-generated samples achieves superior performance compared to counterparts. The additional refinement stage in Condor further enables iterative self-improvement for LLMs at various scales (up to 72B), validating the effectiveness of our approach. Furthermore, our investigation into the scaling for synthetic data in post-training reveals substantial unexplored potential for performance improvements, opening promising avenues for future research.

cs.CL↗

arXiv2024

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game

Despite some promising results in federated learning using game-theoretical methods, most existing studies mainly employ a one-level game in either a cooperative or competitive environment, failing to capture the complex dynamics among participants in practice. To address this issue, we propose DualGFL, a novel Federated Learning framework with a Dual-level Game in cooperative-competitive environments. DualGFL includes a lower-level hedonic game where clients form coalitions and an upper-level multi-attribute auction game where coalitions bid for training participation. At the lower-level DualGFL, we introduce a new auction-aware utility function and propose a Pareto-optimal partitioning algorithm to find a Pareto-optimal partition based on clients' preference profiles. At the upper-level DualGFL, we formulate a multi-attribute auction game with resource constraints and derive equilibrium bids to maximize coalitions' winning probabilities and profits. A greedy algorithm is proposed to maximize the utility of the central server. Extensive experiments on real-world datasets demonstrate DualGFL's effectiveness in improving both server utility and client utility.

cs.GT↗

arXiv2024

LaMI-GO: Latent Mixture Integration for Goal-Oriented Communications Achieving High Spectrum Efficiency

The recent rise of semantic-style communications includes the development of goal-oriented communications (GOCOMs) remarkably efficient multimedia information transmissions. The concept of GO-COMS leverages advanced artificial intelligence (AI) tools to address the rising demand for bandwidth efficiency in applications, such as edge computing and Internet-of-Things (IoT). Unlike traditional communication systems focusing on source data accuracy, GO-COMs provide intelligent message delivery catering to the special needs critical to accomplishing downstream tasks at the receiver. In this work, we present a novel GO-COM framework, namely LaMI-GO that utilizes emerging generative AI for better quality-of-service (QoS) with ultra-high communication efficiency. Specifically, we design our LaMI-GO system backbone based on a latent diffusion model followed by a vector-quantized generative adversarial network (VQGAN) for efficient latent embedding and information representation. The system trains a common feature codebook the receiver side. Our experimental results demonstrate substantial improvement in perceptual quality, accuracy of downstream tasks, and bandwidth consumption over the state-of-the-art GOCOM systems and establish the power of our proposed LaMI-GO communication framework.

cs.LG↗

arXiv2024

Diff-GO$^\text{n}$: Enhancing Diffusion Models for Goal-Oriented Communications

The rapid expansion of edge devices and Internet-of-Things (IoT) continues to heighten the demand for data transport under limited spectrum resources. The goal-oriented communications (GO-COM), unlike traditional communication systems designed for bit-level accuracy, prioritizes more critical information for specific application goals at the receiver. To improve the efficiency of generative learning models for GO-COM, this work introduces a novel noise-restricted diffusion-based GO-COM (Diff-GO$^\text{n}$) framework for reducing bandwidth overhead while preserving the media quality at the receiver. Specifically, we propose an innovative Noise-Restricted Forward Diffusion (NR-FD) framework to accelerate model training and reduce the computation burden for diffusion-based GO-COMs by leveraging a pre-sampled pseudo-random noise bank (NB). Moreover, we design an early stopping criterion for improving computational efficiency and convergence speed, allowing high-quality generation in fewer training steps. Our experimental results demonstrate superior perceptual quality of data transmission at a reduced bandwidth usage and lower computation, making Diff-GO$^\text{n}$ well-suited for real-time communications and downstream applications.

eess.IV↗

arXiv2024

Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations

We introduce CHARM, the first benchmark for comprehensively and in-depth evaluating the commonsense reasoning ability of large language models (LLMs) in Chinese, which covers both globally known and Chinese-specific commonsense. We evaluated 7 English and 12 Chinese-oriented LLMs on CHARM, employing 5 representative prompt strategies for improving LLMs' reasoning ability, such as Chain-of-Thought. Our findings indicate that the LLM's language orientation and the task's domain influence the effectiveness of the prompt strategy, which enriches previous research findings. We built closely-interconnected reasoning and memorization tasks, and found that some LLMs struggle with memorizing Chinese commonsense, affecting their reasoning ability, while others show differences in reasoning despite similar memorization performance. We also evaluated the LLMs' memorization-independent reasoning abilities and analyzed the typical errors. Our study precisely identified the LLMs' strengths and weaknesses, providing the clear direction for optimization. It can also serve as a reference for studies in other fields. We will release CHARM at https://github.com/opendatalab/CHARM .

cs.CL↗

arXiv2024

GTA: A Benchmark for General Tool Agents

Significant focus has been placed on integrating large language models (LLMs) with various tools in developing general-purpose agents. This poses a challenge to LLMs' tool-use capabilities. However, there are evident gaps between existing tool-use evaluations and real-world scenarios. Current evaluations often use AI-generated queries, single-step tasks, dummy tools, and text-only interactions, failing to reveal the agents' real-world problem-solving abilities effectively. To address this, we propose GTA, a benchmark for General Tool Agents, featuring three main aspects: (i) Real user queries: human-written queries with simple real-world objectives but implicit tool-use, requiring the LLM to reason the suitable tools and plan the solution steps. (ii) Real deployed tools: an evaluation platform equipped with tools across perception, operation, logic, and creativity categories to evaluate the agents' actual task execution performance. (iii) Real multimodal inputs: authentic image files, such as spatial scenes, web page screenshots, tables, code snippets, and printed/handwritten materials, used as the query contexts to align with real-world scenarios closely. We design 229 real-world tasks and executable tool chains to evaluate mainstream LLMs. Our findings show that real-world user queries are challenging for existing LLMs, with GPT-4 completing less than 50% of the tasks and most LLMs achieving below 25%. This evaluation reveals the bottlenecks in the tool-use capabilities of current LLMs in real-world scenarios, which provides future direction for advancing general-purpose tool agents. The code and dataset are available at https://github.com/open-compass/GTA.

cs.CL↗

arXiv2024

CIBench: Evaluating Your LLMs with a Code Interpreter Plugin

While LLM-Based agents, which use external tools to solve complex problems, have made significant progress, benchmarking their ability is challenging, thereby hindering a clear understanding of their limitations. In this paper, we propose an interactive evaluation framework, named CIBench, to comprehensively assess LLMs' ability to utilize code interpreters for data science tasks. Our evaluation framework includes an evaluation dataset and two evaluation modes. The evaluation dataset is constructed using an LLM-human cooperative approach and simulates an authentic workflow by leveraging consecutive and interactive IPython sessions. The two evaluation modes assess LLMs' ability with and without human assistance. We conduct extensive experiments to analyze the ability of 24 LLMs on CIBench and provide valuable insights for future LLMs in code interpreter utilization.

cs.CL↗