QLAUN: A Research-Oriented, Robust, Agile, Modular, and Affordable Torque-Controlled Quadruped Robot
QLAUN是一款面向研究、成本低廉的四足机器人，通过3D打印和创新的无电子腿部设计，实现高扭矩输出与模块化，以促进黎巴嫩及MENA地区的机器人学研究。
0 citationsRead paper
Selected work
Representative Papers
New Approximations of Non-Separable MIMO Channels by Separable Channels for Accurate Ergodic Capacity Analysis
This study addresses the analytical complexity and absence of closed-form ergodic capacity solutions in Weichselberger models arising from their non-separable structure. To overcome this, we propose a KL-divergence-based rank-1 decomposition combined with a novel moment-matching method that accurately maps non-separable channels onto separable models. Closed-form capacity expressions are derived across the entire signal-to-noise ratio (SNR) regime, effectively mitigating limitations of conventional approaches under sparse scattering and low-SNR conditions. Results demonstrate that the proposed model achieves significantly higher accuracy than traditional Kronecker models, providing an efficient and analytically tractable theoretical framework for complex MIMO channel analysis.
0 citationsRead paper
DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
This work addresses the challenges of scarce annotations and extreme class imbalance (seizure segments constituting less than 10%) in EEG-based epilepsy detection by proposing the first self-supervised foundation model based on denoising diffusion. The approach employs a 1D U-Net architecture augmented with multi-head self-attention for pretraining on large-scale unlabeled EEG data to learn generalizable neural representations. It further introduces an innovative policy gradient reinforcement learning fine-tuning mechanism that directly optimizes the clinically critical F1 score. Under strict patient-wise evaluation, the model achieves 59% F1 on a four-class seizure subtype classification task, 85% weighted F1 and 59% seizure recall on binary detection, and 97.6% segment-level accuracy, substantially reducing reliance on labeled data while enhancing sensitivity to rare seizure events.
0 citationsRead paper
Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations
This work addresses the fragmentation and lack of behavioral and state consensus in populations of open-weight language models caused by homogeneous routing strategies. The authors propose a multi-agent convention formation framework grounded in the naming game protocol, which constructs a state similarity graph using initial-token scores to distinguish between label agreement and latent state consensus. For the first time in this domain, graph-based feedback control is introduced. The approach incorporates homogeneity-threshold routing, a memory retention mechanism, and a novel bridging strategy that leverages discrepancies in state components and labels to effectively regulate population dynamics. Experiments demonstrate that, in mixed-model grids, bridging routing combined with memory retention achieves behavioral consensus in 14 out of 18 runs; notably, Qwen2.5-32B attains 100% stable consensus under full-history retention, substantially outperforming baseline methods.
0 citationsRead paper
MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
This work addresses a critical gap in existing mathematical reasoning benchmarks, which typically provide complete information and thus fail to evaluate a model’s ability to proactively request missing facts. The authors introduce MIRA-Math, the first benchmark to formalize and assess the diagnostic capability of “minimal information requesting”: given a math problem missing exactly one atomic fact, models must precisely query for the absent information in natural language and, under a strict budget, integrate the retrieved response to produce an exact answer. Through deterministically generated instances, typed prompting protocols, and constrained LLM response channels—augmented by verification and answer-checking mechanisms—the benchmark ensures reproducible evaluation while decoupling information-seeking from reasoning. Experiments across 2,310 instances spanning nine mathematical domains reveal a dissociation between state-of-the-art and smaller models’ success in information requesting versus final answer accuracy, effectively pinpointing critical failure modes in reasoning chains.
0 citationsRead paper
Recent publications
Latest Papers
QLAUN: A Research-Oriented, Robust, Agile, Modular, and Affordable Torque-Controlled Quadruped Robot
QLAUN是一款面向研究、成本低廉的四足机器人，通过3D打印和创新的无电子腿部设计，实现高扭矩输出与模块化，以促进黎巴嫩及MENA地区的机器人学研究。
0 citationsRead paper
New Approximations of Non-Separable MIMO Channels by Separable Channels for Accurate Ergodic Capacity Analysis
This study addresses the analytical complexity and absence of closed-form ergodic capacity solutions in Weichselberger models arising from their non-separable structure. To overcome this, we propose a KL-divergence-based rank-1 decomposition combined with a novel moment-matching method that accurately maps non-separable channels onto separable models. Closed-form capacity expressions are derived across the entire signal-to-noise ratio (SNR) regime, effectively mitigating limitations of conventional approaches under sparse scattering and low-SNR conditions. Results demonstrate that the proposed model achieves significantly higher accuracy than traditional Kronecker models, providing an efficient and analytically tractable theoretical framework for complex MIMO channel analysis.
0 citationsRead paper
DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
This work addresses the challenges of scarce annotations and extreme class imbalance (seizure segments constituting less than 10%) in EEG-based epilepsy detection by proposing the first self-supervised foundation model based on denoising diffusion. The approach employs a 1D U-Net architecture augmented with multi-head self-attention for pretraining on large-scale unlabeled EEG data to learn generalizable neural representations. It further introduces an innovative policy gradient reinforcement learning fine-tuning mechanism that directly optimizes the clinically critical F1 score. Under strict patient-wise evaluation, the model achieves 59% F1 on a four-class seizure subtype classification task, 85% weighted F1 and 59% seizure recall on binary detection, and 97.6% segment-level accuracy, substantially reducing reliance on labeled data while enhancing sensitivity to rare seizure events.
0 citationsRead paper
Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations
This work addresses the fragmentation and lack of behavioral and state consensus in populations of open-weight language models caused by homogeneous routing strategies. The authors propose a multi-agent convention formation framework grounded in the naming game protocol, which constructs a state similarity graph using initial-token scores to distinguish between label agreement and latent state consensus. For the first time in this domain, graph-based feedback control is introduced. The approach incorporates homogeneity-threshold routing, a memory retention mechanism, and a novel bridging strategy that leverages discrepancies in state components and labels to effectively regulate population dynamics. Experiments demonstrate that, in mixed-model grids, bridging routing combined with memory retention achieves behavioral consensus in 14 out of 18 runs; notably, Qwen2.5-32B attains 100% stable consensus under full-history retention, substantially outperforming baseline methods.
0 citationsRead paper
MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
This work addresses a critical gap in existing mathematical reasoning benchmarks, which typically provide complete information and thus fail to evaluate a model’s ability to proactively request missing facts. The authors introduce MIRA-Math, the first benchmark to formalize and assess the diagnostic capability of “minimal information requesting”: given a math problem missing exactly one atomic fact, models must precisely query for the absent information in natural language and, under a strict budget, integrate the retrieved response to produce an exact answer. Through deterministically generated instances, typed prompting protocols, and constrained LLM response channels—augmented by verification and answer-checking mechanisms—the benchmark ensures reproducible evaluation while decoupling information-seeking from reasoning. Experiments across 2,310 instances spanning nine mathematical domains reveal a dissociation between state-of-the-art and smaller models’ success in information requesting versus final answer accuracy, effectively pinpointing critical failure modes in reasoning chains.
0 citationsRead paper