The rapid advancement of pre-trained language models (PLMs) has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. While existing empirical studies evaluate PLMs for vulnerability detection (VD), they suffer from data leakage, limited scope, and superficial analysis, hindering the accuracy and comprehensiveness of evaluations. This paper begins by revisiting the common issues in existing research on PLMs for VD through the evaluation pipeline. It then proceeds with an accurate and extensive evaluation of 18 PLMs on high-quality datasets that feature accurate labeling, diverse vulnerability types, and various projects. Specifically, we compare the performance of PLMs under both fine-tuning and prompt engineering, assess their effectiveness and generalizability across various training and testing settings, and analyze their robustness to a series of perturbations. Our findings reveal that PLMs incorporating pre-training tasks designed to capture the syntactic and semantic patterns of code outperform both general-purpose PLMs and those solely pre-trained or fine-tuned on large code corpora. However, these models face notable challenges in real-world scenarios, such as difficulties in detecting vulnerabilities with complex dependencies, handling perturbations introduced by code normalization and abstraction, and identifying semantic-preserving vulnerable code transformations. Also, the truncation caused by the limited context windows of PLMs can lead to a non-negligible number of labeling errors, which is overlooked by previous work. This study underscores the importance of thorough evaluations of model performance in practical scenarios and outlines future directions to help enhance the effectiveness of PLMs for realistic VD applications.

AI Video Chat emerges as a new paradigm for Real-time Communication (RTC), where one peer is not a human, but a Multimodal Large Language Model (MLLM). This makes interaction between humans and AI more intuitive, as if chatting face-to-face with a real person. However, this poses significant challenges to latency, because the MLLM inference takes up most of the response time, leaving very little time for video streaming. Due to network uncertainty, transmission latency becomes a critical bottleneck preventing AI from being like a real person. To address this, we call for AI-oriented RTC research, exploring the network requirement shift from "humans watching video" to "AI understanding video". We begin by recognizing the main differences between AI Video Chat and traditional RTC. Then, through prototype measurements, we identify that ultra-low bitrate is a key factor for low latency. To reduce bitrate dramatically while maintaining MLLM accuracy, we propose Context-Aware Video Streaming that recognizes the importance of each video region for chat and allocates bitrate almost exclusively to chat-important regions. To evaluate the impact of video streaming quality on MLLM accuracy, we build the first benchmark, named Degraded Video Understanding Benchmark (DeViBench). Finally, we discuss some open questions and ongoing solutions for AI Video Chat. DeViBench is open-sourced at: https://github.com/pku-netvideo/DeViBench.

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant storage burden for an edge device. To address this challenge, we consider a scenario where experts are dispersed across an edge network for distributed inference. Based on the popular Top-$K$ expert selection strategy, we formulate a latency minimization problem by optimizing expert caching on edge servers under storage constraints. When $K=1$, the problem reduces to a monotone submodular maximization problem with knapsack constraints, for which we design a greedy-based algorithm with a $(1 - 1/e)$-approximation guarantee. For the general case where $K \geq 1$, expert co-activation within the same MoE layer introduces non-submodularity, which renders greedy methods ineffective. To tackle this issue, we propose a successive greedy decomposition method to decompose the original problem into a series of subproblems, with each being solved by a dynamic programming approach. Furthermore, we design an accelerated algorithm based on the max-convolution technique to obtain the approximate solution with a provable guarantee in polynomial time. Simulation results on various MoE models demonstrate that our method significantly reduces inference latency compared to existing baselines.

Vision-Language-Action (VLA) models have emerged as a promising framework for enabling generalist robots capable of perceiving, reasoning, and acting in the real world. These models usually build upon pretrained Vision-Language Models (VLMs), which excel at semantic understanding due to large-scale image and text pretraining. However, existing VLMs typically lack precise spatial understanding capabilities, as they are primarily tuned on 2D image-text pairs without 3D supervision. To address this limitation, recent approaches have incorporated explicit 3D inputs such as point clouds or depth maps, but this necessitates additional depth sensors or pre-trained depth estimation models, which may yield defective results. In contrast, our work introduces a plug-and-play module that implicitly incorporates 3D geometry features into VLA models by leveraging an off-the-shelf visual geometry foundation model. This integration provides the model with depth-aware visual representations, improving its ability to understand the geometric structure of the scene and the spatial relationships among objects from RGB images alone. We evaluate our method on a set of spatially challenging tasks in both simulation and the real world. Extensive evaluations show that our method significantly improves the performance of state-of-the-art VLA models across diverse scenarios.

Surface electromyography (sEMG) signals show promise for effective human-machine interfaces, particularly in rehabilitation and prosthetics. However, challenges remain in developing systems that respond quickly to user intent, produce stable flicker-free output suitable for device control, and work across different subjects without time-consuming calibration. In this work, we propose a framework for EMG-based intent detection that addresses these challenges. We cast intent detection as per-timestep segmentation of continuous sEMG streams, assigning labels as gestures unfold in real time. We introduce a masked modeling training strategy that aligns muscle activations with their corresponding user intents, enabling rapid onset detection and stable tracking of ongoing gestures. In evaluations against baseline methods, using metrics that capture accuracy, latency and stability for device control, our approach achieves state-of-the-art performance in zero-shot conditions. These results demonstrate its potential for wearable robotics and next-generation prosthetic systems. Our project website, video, code, and dataset are available at: https://reactemg.github.io/

Background: User reviews of Telehealth and Patient Portal mobile applications (apps) hereon referred to as electronic health (eHealth) apps are a rich source of unsolicited patient feedback, revealing critical insights into patient perceptions. However, the lack of large-scale, annotated datasets specific to privacy and trust has limited the ability of researchers to systematically analyze these concerns using natural language processing (NLP) techniques. Objective: This study aims to develop and benchmark Health App Reviews for Privacy & Trust (HARPT), a large-scale annotated corpus of patient reviews from eHealth apps to advance research in patient privacy and trust. Methods: We employed a multistage data construction strategy. This integrated keyword-based filtering, iterative manual labeling with review, targeted data augmentation, and weak supervision using transformer-based classifiers. A curated subset of 7,000 reviews was manually annotated to support machine learning model development and evaluation. The resulting dataset was used to benchmark a broad range of models. Results: The HARPT corpus comprises 480,000 patient reviews annotated across seven categories capturing critical aspects of trust in the application (TA), trust in the provider (TP), and privacy concerns (PC). We provide comprehensive benchmark performance for a range of machine learning models on the manually annotated subset, establishing a baseline for future research. Conclusions: The HARPT corpus is a significant resource for advancing the study of privacy and trust in the eHealth domain. By providing a large-scale, annotated dataset and initial benchmarks, this work supports reproducible research in usable privacy and trust within health informatics. HARPT is released under an open resource license.

Accurate typhoon track forecasting is crucial for early system warning and disaster response. While Transformer-based models have demonstrated strong performance in modeling the temporal dynamics of dense trajectories of humans and vehicles in smart cities, they usually lack access to broader contextual knowledge that enhances the forecasting reliability of sparse meteorological trajectories, such as typhoon tracks. To address this challenge, we propose TyphoFormer, a novel framework that incorporates natural language descriptions as auxiliary prompts to improve typhoon trajectory forecasting. For each time step, we use Large Language Model (LLM) to generate concise textual descriptions based on the numerical attributes recorded in the North Atlantic hurricane database. The language descriptions capture high-level meteorological semantics and are embedded as auxiliary special tokens prepended to the numerical time series input. By integrating both textual and sequential information within a unified Transformer encoder, TyphoFormer enables the model to leverage contextual cues that are otherwise inaccessible through numerical features alone. Extensive experiments are conducted on HURDAT2 benchmark, results show that TyphoFormer consistently outperforms other state-of-the-art baseline methods, particularly under challenging scenarios involving nonlinear path shifts and limited historical observations.

Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexplored. Current approaches predominantly rely on either the next-token prediction loss of supervised fine-tuning (SFT) or recommendationspecific direct preference optimization (DPO) strategies. Both methods ignore the exploration of possible positive unobserved samples, which is commonly referred to as the exposure bias problem. To mitigate this problem, this paper treats the GR as a multi-step generation task and constructs a GFlowNets-based fine-tuning framework (GFlowGR). The proposed framework integrates collaborative knowledge from traditional recommender systems to create an adaptive trajectory sampler and a comprehensive reward model. Leveraging the diverse generation property of GFlowNets, along with sampling and heuristic weighting techniques, GFlowGR emerges as a promising approach to mitigate the exposure bias problem. Extensive empirical results on two real-world datasets and with two different GR backbones highlight the effectiveness and robustness of GFlowGR.

Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often rigid. They struggle to adapt to diverse reasoning structures, from formal proofs to informal natural language narratives. To address this adaptability gap, we propose the Graph of Verification (GoV), a novel framework for adaptable and multi-granular verification. GoV's core innovation is its flexible "node block" architecture. This mechanism allows GoV to adaptively adjust its verification granularity--from atomic steps for formal tasks to entire paragraphs for natural language--to match the native structure of the reasoning process. This flexibility allows GoV to resolve the fundamental trade-off between verification precision and robustness. Experiments on both well-structured and loosely-structured benchmarks demonstrate GoV's versatility. The results show that GoV's adaptive approach significantly outperforms both holistic baselines and other state-of-the-art decomposition-based methods, establishing a new standard for training-free reasoning verification.

As large language models (LLMs) are progressively deployed in various real-world applications, personalization of LLMs has become increasingly important. While various approaches to LLM personalization such as prompt-based and training-based methods have been actively explored, the development of effective decoding-time algorithms remains largely overlooked, despite their demonstrated potential. In this paper, we propose CoPe (Contrasting Personal Preference), a novel decoding-time approach applied after performing parameter-efficient fine-tuning (PEFT) on user-specific data. Our core idea is to leverage reward-guided decoding specifically for personalization by maximizing each user's implicit reward signal. We evaluate CoPe across five open-ended personalized text generation tasks. Our empirical results demonstrate that CoPe achieves strong performance, improving personalization by an average of 10.57% in ROUGE-L, without relying on external reward models or additional training procedures.