15 accepted papers
Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture domain-specific information, thus enabling domain-aware decision making…
Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness…
Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance gains: (1) non-stationary Q-value estimation stemming from the joint injection of entropy and the concurrent u…
Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to specific needs, they often require costly data curation and additional training. Test-time scaling (TTS) presents an efficient, training-free altern…
Time series forecasting is crucial for applications in various domains. Conventional methods often rely on global decomposition into trend, seasonal, and residual components, which become ineffective for real-world series dominated by local, complex, and highly dynamic patterns. Moreover, the high m
Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute…
Policies developed through Reinforcement Learning (RL) and Imitation Learning (IL) have shown great potential in continuous control tasks, but real-world applications often require adapting trained policies to unforeseen requirements. While fine-tuning can address such needs, it typically requires a…
The increasing scale of large language models (LLMs) brings emergent abilities to various complex tasks requiring reasoning, such as arithmetic and commonsense reasoning. It is known that the effective design of task-specific prompts is critical for LLMs’ ability to produce high-quality answers. In…
New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present a meticulously designed evaluation benchmark that leverages the knowledge graph. This evaluation comprises 584 level-1 knowledge points and 1,989 level-2 knowledge points, thereby e…
Table data is pervasive in various industries, and its comprehension and manipulation demand significant time and effort for users seeking to extract relevant information. Consequently, an increasing number of studies have been directed towards table-to-text generation tasks. However, most existing…
Evidence-aware fake news detection aims to determine the veracity of a given news (i.e., claim) with external evidences. We find that existing methods lack sufficient semantic perception and are easily blinded by textual expressions. For example, they still make the same prediction after we flip the…
Video de-raining is an important yet highly challenging task in the field of computer vision. Though numerous video de-raining methods are developed with encouraging performance, two major challenges for video de-raining are still unsatisfactorily solved and need to be further investigated as follow…
Channel pruning is a promising technique of model compression and acceleration because it reduces the space and time complexity of convolutional neural networks (CNNs) while maintaining their performance. In existing methods, channel pruning is performed by iterative optimization or training with sp…
The sparse array design for adaptive beamforming has been recently formulated into combinatorial antenna selection problems, which belong to notorious NP-hard problems. As the commonly deployed convex relaxation algorithms are susceptible to local optima, several trials with different initial points…
We present trajectory tracking and balance control of an autonomous bikebot. The bikebot is a single-track autonomous mobile robot that is designed to study unstable physical human-robot interactions. The controller is built on the property of the external-internal convertible (EIC) structure for th…