27 accepted papers
Traditional value models $V^{\pi}$ in LLM reinforcement learning face a coupling dilemma: they require synchronous training alongside the updating policy $\pi$, causing inefficiency and overfitting. In this paper, we propose $V_0$, a generalist value model that decouples value estimation from specif…
As LLM-based agents are increasingly deployed in real-world workflows, existing agent benchmarks---often built on idealized, noise-free assumptions---fall short of characterizing agents' robustness under imperfect user instructions and unreliable tool feedback. To address this gap, we introduce **Ag…
Forecasting geostationary infrared brightness temperature sequences from historical observations is a significant and challenging task. By analyzing these predictions, cloud evolution, convective activity, and atmospheric radiative states can be revealed in advance, offering high potential value in
Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent capability asymmetry between generation and self-verificatio…
Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as text, where token-level cost is uniform and scales linearly with length, often spending scarce budget on low-value detail…
Solar irradiance forecast aims to accurately estimate future solar irradiance based on historical data, playing a vital role in energy production and grid management. While ground-based station measurements provide local accuracy, geostationary satellites offer much broader environmental contexts,
Equipping agents with interactive environments and verifiable tasks for self-exploration is essential for cultivating generalist agents capable of adapting to diverse scenarios. However, high-quality agentic data remain critically scarce, and existing synthesis methods suffer from significant limita…
As LLMs with agentic abilities are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic user interactions. To address this gap, we introduce VitaBench, a chall…
Large Multimodal Models (LMMs) have recently demonstrated impressive performance on general video comprehension benchmarks. Nevertheless, for broader applications, the robustness of their temporal analysis capability needs to be thoroughly investigated yet predominantly ignored. Motivated by this, w…
Large Language Models (LLMs) are primarily designed for batch processing. Existing methods for adapting LLMs to streaming rely either on expensive re-encoding or specialized architectures with limited scalability. This work identifies three key mismatches in adapting batch-oriented LLMs to streaming…
Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performance. However, the integration of multi-layer visual features in MLLMs remains underexplored, particularly with regard to…
Multi-condition information retrieval (IR) presents a significant, yet underexplored challenge for existing systems. This paper introduces MultiConIR, the first benchmark specifically designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios across five divers
Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than principled analysis. While prior studies suggest that different V
Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies, but conventional static pruning methods overlook two critical…
Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted growing interest in distilling CoT capabilities into Small Language Models (SLMs). This study systematically examines the…
Multimodal Large Language Models (MLLMs) have achieved strong performance across vision-language tasks, but suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens. Though efforts have been made to prune tokens in MLLM
Accurate text summarization is one of the most common and important tasks performed by Large Language Models, where the costs of human review for an entire document may be high, but the costs of errors in summarization may be even greater. We propose Detecting Errors through Ensembling Prompts (DEEP…
Prompt-based paradigm has shown its competitive performance in many NLP tasks. However, its success heavily depends on prompt design, and the effectiveness varies upon the model and training data. In this paper, we propose a novel dual context-guided continuous prompt (DCCP) tuning method. To explor…
Large-scale pretrained language models have achieved SOTA results on NLP tasks. However, they have been shown vulnerable to adversarial attacks especially for logographic languages like Chinese. In this work, we propose RoCBert: a pretrained Chinese Bert that is robust to various forms of adversaria…
We propose a generative probabilistic model for human motion synthesis. Our model has a hierarchy of three layers. At the bottom layer, we utilize Hidden semi-Markov Model (HSMM), which explicitly models the spatial pose, temporal transition and speed variations in motion sequences. At the middle la…
The use of social media runs through our lives, and users' emotions are also affected by it. Previous studies have reported social organizations and psychologists using social media to find depressed patients. However, due to the variety of content published by users, it isn't effortless for the sys…
We propose a framework for recognizing human actions from skeleton data by modeling the underlying dynamic process that generates the motion pattern. We capture three major factors that contribute to the complexity of the motion pattern including spatial dependencies among body joints, temporal depe…
Human action recognition remains as a challenging task partially due to the presence of large variations in the execution of action. To address this issue, we propose a probabilistic model called Hierarchical Dynamic Model (HDM). Leveraging on Bayesian framework, the model parameters are allowed to…
Existing deep learning based facial landmark detection methods have achieved excellent performance. These methods, however, do not explicitly embed the structural dependencies among landmark points. They hence cannot preserve the geometric relationships between landmark points or generalize well to…
Deep neural networks achieve good performance in many computer vision problems such as face alignment. However, when the testing image is challenging due to low resolution, occlusion or adversarial attacks, the accuracy of a deep neural network suffers greatly. Therefore, it is important to quantify…
Existing appearance-based gaze estimation approaches with CNN have poor generalization performance. By systematically studying this issue, we identify three major factors: 1) appearance variations; 2) head pose variations and 3) over-fitting issue with point estimation. To improve the generalization…
Generalizing eye tracking to new subjects/environments remains challenging for existing appearance-based methods. To address this issue, we propose to leverage on eye movement dynamics inspired by neurological studies. Studies show that there exist several common eye movement types, independent of v…