Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?

Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively studied in models trained from scratch, the impact of LLMs' prior knowledge on calibration during fine-tuning remains understudied. Our research reveals that LLMs' prior knowledge causes potential poor calibration due to the ubiquitous presence of known data in real-world fine-tuning, which appears harmful for calibration. Specifically, data aligned with LLMs' prior knowledge would induce overconfidence, while new knowledge improves calibration. Our findings expose a tension: LLMs' encyclopedic knowledge, while enabling task versatility, undermines calibration through unavoidable knowledge overlaps. To address this, we propose CogCalib, a cognition-aware framework that applies targeted learning strategies according to the model's prior knowledge. Experiments across 7 tasks using 3 LLM families prove that CogCalib significantly improves calibration while maintaining performance, achieving an average 57\% reduction in ECE compared to standard fine-tuning in Llama3-8B. These improvements generalize well to out-of-domain tasks, enhancing the objectivity and reliability of domain-specific LLMs, and making them more trustworthy for critical human-AI interaction applications.

Equivariant Flow Matching for Point Cloud Assembly

The goal of point cloud assembly is to reconstruct a complete 3D shape by aligning multiple point cloud pieces. This work presents a novel equivariant solver for assembly tasks based on flow matching models. We first theoretically show that the key to learning equivariant distributions via flow matching is to learn related vector fields. Based on this result, we propose an assembly model, called equivariant diffusion assembly (Eda), which learns related vector fields conditioned on the input pieces. We further construct an equivariant path for Eda, which guarantees high data efficiency of the training process. Our numerical results show that Eda is highly competitive on practical datasets, and it can even handle the challenging situation where the input pieces are non-overlapped.

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning

Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fine-tuning a scoring model on the target dataset, which is time-consuming and resource-intensive, or rely on heuristics that fail to fully leverage the model's predictive capabilities. To address these challenges, we propose Data Whisperer, an efficient, training-free, attention-based method that leverages few-shot in-context learning with the model to be fine-tuned. Comprehensive evaluations were conducted on both raw and synthetic datasets across diverse tasks and models. Notably, Data Whisperer achieves superior performance compared to the full GSM8K dataset on the Llama-3-8B-Instruct model, using just 10% of the data, and outperforms existing methods with a 3.1-point improvement and a 7.4$\times$ speedup.

ASRC-SNN: Adaptive Skip Recurrent Connection Spiking Neural Network

In recent years, Recurrent Spiking Neural Networks (RSNNs) have shown promising potential in long-term temporal modeling. Many studies focus on improving neuron models and also integrate recurrent structures, leveraging their synergistic effects to improve the long-term temporal modeling capabilities of Spiking Neural Networks (SNNs). However, these studies often place an excessive emphasis on the role of neurons, overlooking the importance of analyzing neurons and recurrent structures as an integrated framework. In this work, we consider neurons and recurrent structures as an integrated system and conduct a systematic analysis of gradient propagation along the temporal dimension, revealing a challenging gradient vanishing problem. To address this issue, we propose the Skip Recurrent Connection (SRC) as a replacement for the vanilla recurrent structure, effectively mitigating the gradient vanishing problem and enhancing long-term temporal modeling performance. Additionally, we propose the Adaptive Skip Recurrent Connection (ASRC), a method that can learn the skip span of skip recurrent connection in each layer of the network. Experiments show that replacing the vanilla recurrent structure in RSNN with SRC significantly improves the model's performance on temporal benchmark datasets. Moreover, ASRC-SNN outperforms SRC-SNN in terms of temporal modeling capabilities and robustness.

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making in complex 3D environments, which demand second-level responses, high-resolution perception, and tactical reasoning under dynamic conditions. To advance the field, we introduce CombatVLA, an efficient VLA model optimized for combat tasks in 3D action role-playing games(ARPGs). Specifically, our CombatVLA is a 3B model trained on video-action pairs collected by an action tracker, where the data is formatted as action-of-thought (AoT) sequences. Thereafter, CombatVLA seamlessly integrates into an action execution framework, allowing efficient inference through our truncated AoT strategy. Experimental results demonstrate that CombatVLA not only outperforms all existing models on the combat understanding benchmark but also achieves a 50-fold acceleration in game combat. Moreover, it has a higher task success rate than human players. We will open-source all resources, including the action tracker, dataset, benchmark, model weights, training code, and the implementation of the framework at https://combatvla.github.io/.

FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis

Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own, often for humor, provocation, or controversy. Detecting and analyzing parody can be challenging and is often reliant on context, yet it plays a crucial role in understanding cultural values, promoting subcultures, and enhancing self-expression. However, the study of parody is hindered by limited available data and deficient diversity in current datasets. To bridge this gap, we built seven parody datasets from both English and Chinese corpora, with 14,755 annotated users and 21,210 annotated comments in total. To provide sufficient context information, we also collect replies and construct user-interaction graphs to provide richer contextual information, which is lacking in existing datasets. With these datasets, we test traditional methods and Large Language Models (LLMs) on three key tasks: (1) parody detection, (2) comment sentiment analysis with parody, and (3) user sentiment analysis with parody. Our extensive experiments reveal that parody-related tasks still remain challenging for all models, and contextual information plays a critical role. Interestingly, we find that, in certain scenarios, traditional sentence embedding methods combined with simple classifiers can outperform advanced LLMs, i.e. DeepSeek-R1 and GPT-o3, highlighting parody as a significant challenge for LLMs.

A Deep Learning Framework with Geographic Information Adaptive Loss for Remote Sensing Images based UAV Self-Positioning

With the expanding application scope of unmanned aerial vehicles (UAVs), the demand for stable UAV control has significantly increased. However, in complex environments, GPS signals are prone to interference, resulting in ineffective UAV positioning. Therefore, self-positioning of UAVs in GPS-denied environments has become a critical objective. Some methods obtain geolocation information in GPS-denied environments by matching ground objects in the UAV viewpoint with remote sensing images. However, most of these methods only provide coarse-level positioning, which satisfies cross-view geo-localization but cannot support precise UAV positioning tasks. Consequently, this paper focuses on a newer and more challenging task: precise UAV self-positioning based on remote sensing images. This approach not only considers the features of ground objects but also accounts for the spatial distribution of objects in the images. To address this challenge, we present a deep learning framework with geographic information adaptive loss, which achieves precise localization by aligning UAV images with corresponding satellite imagery in fine detail through the integration of geographic information from multiple perspectives. To validate the effectiveness of the proposed method, we conducted a series of experiments. The results demonstrate the method's efficacy in enabling UAVs to achieve precise self-positioning using remote sensing imagery.

ChineseSimpleVQA -- "See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models

The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability. In this paper, we introduce the first factuality-based visual question-answering benchmark in Chinese, named ChineseSimpleVQA, aimed at assessing the visual factuality of LVLMs across 8 major topics and 56 subtopics. The key features of this benchmark include a focus on the Chinese language, diverse knowledge types, a multi-hop question construction, high-quality data, static consistency, and easy-to-evaluate through short answers. Moreover, we contribute a rigorous data construction pipeline and decouple the visual factuality into two parts: seeing the world (i.e., object recognition) and discovering knowledge. This decoupling allows us to analyze the capability boundaries and execution mechanisms of LVLMs. Subsequently, we evaluate 34 advanced open-source and closed-source models, revealing critical performance gaps within this field.

FAST-LIVO2 on Resource-Constrained Platforms: LiDAR-Inertial-Visual Odometry with Efficient Memory and Computation

This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with sequential updates, improving computation efficiency significantly while maintaining a similar level of robustness. Additionally, a memory-efficient mapping structure combining a locally unified visual-LiDAR map and a long-term visual map achieves a good trade-off between performance and memory usage. Extensive experiments on x86 and ARM platforms demonstrate the system's robustness and efficiency. On the Hilti dataset, our system achieves a 33% reduction in per-frame runtime and 47% lower memory usage compared to FAST-LIVO2, with only a 3 cm increase in RMSE. Despite this slight accuracy trade-off, our system remains competitive, outperforming state-of-the-art (SOTA) LIO methods such as FAST-LIO2 and most existing LIVO systems. These results validate the system's capability for scalable deployment on resource-constrained edge computing platforms.

Procedural Fairness and Its Relationship with Distributive Fairness in Machine Learning

Fairness in machine learning (ML) has garnered significant attention in recent years. While existing research has predominantly focused on the distributive fairness of ML models, there has been limited exploration of procedural fairness. This paper proposes a novel method to achieve procedural fairness during the model training phase. The effectiveness of the proposed method is validated through experiments conducted on one synthetic and six real-world datasets. Additionally, this work studies the relationship between procedural fairness and distributive fairness in ML models. On one hand, the impact of dataset bias and the procedural fairness of ML model on its distributive fairness is examined. The results highlight a significant influence of both dataset bias and procedural fairness on distributive fairness. On the other hand, the distinctions between optimizing procedural and distributive fairness metrics are analyzed. Experimental results demonstrate that optimizing procedural fairness metrics mitigates biases introduced or amplified by the decision-making process, thereby ensuring fairness in the decision-making process itself, as well as improving distributive fairness. In contrast, optimizing distributive fairness metrics encourages the ML model's decision-making process to favor disadvantaged groups, counterbalancing the inherent preferences for advantaged groups present in the dataset and ultimately achieving distributive fairness.