38 accepted papers
Diffusion language models (DLMs) have recently emerged as an alternative to autoregressive approaches, enabling parallel sequence generation and flexible token generation orders. Machine unlearning plays a critical role in mitigating legal and ethical risks by removing the influence of specific trai…
Reward models trained on human preference data have demonstrated strong effectiveness in aligning Large Language Models (LLMs) with human intent under the framework of Reinforcement Learning from Human Feedback (RLHF). However, RLHF remains vulnerable to reward hacking, where the policy exploits imp…
Safety remains one of the most critical challenges in autonomous driving systems. In recent years, the end-to-end driving has shown great promise in advancing vehicle autonomy in a scalable manner. However, existing approaches often face safety risks due to the lack of explicit behavior constraints.…
Multivariate time series forecasting is crucial across a wide range of domains. While presenting notable progress for the Transformer architecture, iTransformer still lags behind the latest MLP-based models. We attribute this performance gap to unstable inter-channel relationships. To bridge this ga
Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing evaluation approaches, relying on model heuristics, expert rubrics, or user simulation, fail to capture the diversity an…
As Large Language Models (LLMs) are increasingly applied in high-stakes domains, their ability to reason strategically under uncertainty becomes critical. Poker provides a rigorous testbed, requiring not only strong actions but also principled, game-theoretic reasoning. In this paper, we conduct a s…
Autoformalization—the process of converting natural language mathematical statements into machine-verifiable formal code—plays a critical role in ensuring the reliability of mathematical reasoning generated by large language models (LLMs). Recent studies show that LLMs exhibit strong potential in au…
Long-context inference in large language models is bottlenecked by Key-Value (KV) cache loading during the decoding stage, where the sequential nature of generation requires repeatedly transferring the KV cache from off-chip to on-chip memory at each step. Recent architectures like Multi-Head Latent…
Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models (LLMs) with human preferences. However, reward-based methods built on the Bradley–Terry assumption struggle to capture the non-transitive and heterogeneous nature of real-world p…
High-quality training data is critical to the performance of large language models (LLMs). Recent work has explored using LLMs to rate and select data based on a small set of human-designed criteria (rules), but these approaches often rely heavily on heuristics, lack principled metrics for rule eval
As Multimodal Large Language Models (MLLMs) continue to be trained, the availability of public data diminishes, limiting the possibility for further training and adaptation. However, private data remains an underutilized yet valuable resource. Federated Learning (FL) enables decentralized training o…
Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent proposes plans and monitors progress while a reasoning agent execut…
Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full generative potential remains an underexplored challenge. To
Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world problems are multi-stage complex tasks, composed of a seque…
Large Multimodal Models (LMMs) has demonstrated capabilities across various domains, but comprehensive benchmarks for agricultural remote sensing (RS) remain scarce. Existing benchmarks designed for agricultural RS scenarios exhibit notable limitations, primarily in terms of insufficient scene diver…
Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensitive nature of their training data, which can include copyrighted and private con…
Safety remains one of the most critical challenges in autonomous driving systems. In recent years, the end-to-end driving has shown great promise in advancing vehicle autonomy in a scalable manner. However, existing approaches often face safety risks due to the lack of explicit behavior constraints.
In-context learning (ICL) effectively conditions large language models (LLMs) for molecular tasks, such as property prediction and molecule captioning, by embedding carefully selected demonstration examples into the input prompt. This approach eliminates the computational overhead of extensive pre-t
Agricultural parcels serve as basic units for conducting agricultural practices and applications, which is vital for land ownership registration, food security assessment, soil erosion monitoring, etc. However, existing agriculture parcel extraction studies only focus on mid-resolution mapping or re…
In complex missions such as search and rescue, robots must make intelligent decisions in unknown environments, relying on their ability to perceive and understand their surroundings. High-quality and real-time reconstruction enhances situational awareness and is crucial for intelligent robotics. Tra
Although state-of-the-art (SOTA) SAT solvers based on conflict-driven clause learning (CDCL) have achieved remarkable engineering success, their sequential nature limits the parallelism that may be extracted for acceleration on platforms such as the graphics processing unit (GPU). In this work, we p…
Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their real-world adoption. Despite initial efforts to defend against…
Reinforcement Learning from Human Feedback (RLHF) is widely used to align models with human preferences, particularly to enhance the safety of responses generated by LLMs. This method traditionally relies on choosing preferred responses from response pairs. However, due to variations in human opinio…
Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the computational cost of the diffusion model to scale linearly w…
Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising and previously overlooked phenomenon: explicit CoT reasoning…
Graph contrastive learning has made remarkable advances in settings where there is a scarcity of task-specific labels. Despite these advances, the significant computational overhead for representation inference incurred by existing methods that rely on intensive message passing makes them unsuitable…
Diffusion models have exhibited remarkable advancements in generating high-quality data. However, a critical drawback is their computationally intensive inference process, which requires a large number of timesteps to generate a single sample. Existing methods address this challenge by decoupling th…
Online dense mapping of urban scenes forms a fundamental cornerstone for scene understanding and navigation of autonomous vehicles. Recent advancements in dense mapping methods are mainly based on NeRF, whose rendering speed is too slow to meet online requirements. 3D Gaussian Splatting (3DGS), with
The advance of unmanned aerial vehicles (UAVs) has enabled customers and directors to film from the air. However, operating the drone to produce desired videos upon a moving object is hard to achieve. This letter proposes an autonomous aerial videography system that integrates customized shots and d
3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation. In this task, we notice that images could provide rich texture, color, and discriminative information, which can complement LiDAR data for evident performance improvement, bu…
Determining the satisfiability of Boolean constraint-satisfaction problems with different types of constraints, that is hybrid constraints, is a well-studied problem with important applications. We study a new application of hybrid Boolean constraints, which arises in quantum computing. The problem…
We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforcement learning algorithms have demonstrated promising results in accelerating th…
Scientific claim verification can help the researchers to easily find the target scientific papers with the sentence evidence from a large corpus for the given claim. Some existing works propose pipeline models on the three tasks of abstract retrieval, rationale selection and stance prediction. Such…
The quadrotor is popularly used in challenging environments due to its superior agility and flexibility. In these scenarios, trajectory planning plays a vital role in generating safe motions to avoid obstacles while ensuring flight smoothness. Although many works on quadrotor planning have been prop…
The development of aerial autonomy has enabled aerial robots to fly agilely in complex environments. However, dodging fast-moving objects in flight remains a challenge, limiting the further application of unmanned aerial vehicles (UAVs). The bottleneck of solving this problem is the accurate percept…
We explore the potential of continuous local search (CLS) in SAT solving by proposing a novel approach for finding a solution of a hybrid system of Boolean constraints. The algorithm is based on CLS combined with belief propagation on binary decision diagrams (BDDs). Our framework accepts all Boolea…
One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neur…
This paper presents a novel nonlinear compliant link. It has two major properties: bi-directionality and stiffening compliance. Bi-directionality means it can be stretched and compressed, and is realized by antagonistic arrangement of an extension spring and a compression spring. Stiffening complian…