Zhengyang Zhao

Zhengyang Zhao, Lu Ma, Yizhen Jiang et al.

The prevailing post-training paradigm for Large Reasoning Models (LRMs)--Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL)--suffers from an intrinsic optimization mismatch: the rigid supervision inherent in SFT induces distributional collapse, thereby exhausting the exploration space necessary for subsequent RL. In this paper, we reformulate SFT within a unified post-training framework and propose Gibbs Initialization with Finite Temperature (GIFT). We characterize standard SFT as a degenerate zero-temperature limit that suppresses base priors. Conversely, GIFT incorporates supervision as a finite-temperature energy potential, establishing a distributional bridge that ensures objective consistency throughout the post-training pipeline. Our experiments demonstrate that GIFT significantly outperforms standard SFT and other competitive baselines when utilized for RL initialization, providing a mathematically principled pathway toward achieving global optimality in post-training. Our code is available at https://github.com/zzy1127/GIFT.

Ziming Wan, Deqing Wang, Xuehua Ming et al.

Heterogeneous graph neural networks (HGNNs) have been widely applied in heterogeneous information network tasks, while most HGNNs suffer from poor scalability or weak representation when they are applied to large-scale heterogeneous graphs. To address these problems, we propose a novel Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning (RHCO) for large-scale heterogeneous graph representation learning. Unlike traditional heterogeneous graph neural networks, we adopt the contrastive learning mechanism to deal with the complex heterogeneity of large-scale heterogeneous graphs. We first learn relation-aware node embeddings under the network schema view. Then we propose a novel positive sample selection strategy to choose meaningful positive samples. After learning node embeddings under the positive sample graph view, we perform a cross-view contrastive learning to obtain the final node representations. Moreover, we adopt the label smoothing technique to boost the performance of RHCO. Extensive experiments on three large-scale academic heterogeneous graph datasets show that RHCO achieves best performance over the state-of-the-art models.

Zheng Zhang, Fan Yang, Ziyan Jiang et al. · amazon-science

Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in long inputs. However, recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information within the input sequence. In this study, we conduct extensive experiments to investigate the root causes of positional bias. Our findings indicate that the primary contributor to LLM positional bias stems from the inherent positional preferences of different models. We demonstrate that merely employing prompt-based solutions is inadequate for overcoming the positional preferences. To address this positional bias issue of a pre-trained LLM, we developed a Position-Aware Parameter Efficient Fine-Tuning (PAPEFT) approach which is composed of a data augmentation technique and a parameter efficient adapter, enhancing a uniform attention distribution across the input context. Our experiments demonstrate that the proposed approach effectively reduces positional bias, improving LLMs' effectiveness in handling long context sequences for various tasks that require externally retrieved knowledge.

Salonik Resch, Zamshed I. Chowdhury, Husrev Cilasun et al.

Beyond edge devices can function off the power grid and without batteries, enabling them to operate in difficult to access regions. However, energy costly long-distance communication required for reporting results or offloading computation becomes a limitation. Here, we reduce this overhead by developing a beyond edge device which can effectively act as a nearby server to offload computation. For security reasons, this device must operate on encrypted data, which incurs a high overhead. We use energy-efficient and intermittent-safe in-memory computation to enable this encrypted computation, allowing it to provide a speedup for beyond edge applications within a power budget of a few milliWatts.