27 accepted papers
The alignment of Large Language Models (LLMs) with human preferences is critically undermined by noisy labels in training datasets. Existing robust methods often prove insufficient, as they rely on single, narrow heuristics such as perplexity or loss, failing to address the diverse nature of real-wo…
Multi-agent deep Reinforcement Learning (RL) has made significant progress in developing intelligent game-playing agents in recent years. However, the efficient training of collective robots using multi-agent RL and the transfer of learned policies to real-world applications remain open research que…
We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance by challenging the trend of architectural complexity. Instead of intricate, multi-stream designs, CrystalDiT employs a unified transformer that imposes a powerful inductive bias
Direct Preference Optimization (DPO) has become the dominant approach for aligning large language models with human preferences. However, standard DPO treats all preference pairs uniformly, overlooking the heterogeneous nature of the learning problem: some samples demand sophisticated semantic under…
Direct Preference Optimization (DPO) has become a predominant approach for aligning large language models with human preferences. Recent work has used perplexity differentials to identify unreliable preference labels, but these methods apply uniform calibration strategies across all samples. We obse…
Existing LLM-based agents have achieved strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. Hence, some recent work focus on fine-tuning the policy model with more diverse tasks to improve the generalizability. In this work, we find that finetuning a reward…
Positional bias in large language models hinders their ability to effectively process long inputs. A prominent example is the “lost in the middle” phenomenon, where LLMs struggle to utilize relevant information situated in the middle of the input. While prior research primarily focuses on single pie…
Large Language Models (LLMs) excel in traditional natural language processing tasks but struggle with problems that require complex domain-specific calculations or simulations. While equipping LLMs with external tools to build LLM-based agents can enhance their capabilities, existing approaches lack…
Recent efforts to employ large language models (LLMs) as agents have demonstrated promising results in a wide range of multi-step agent tasks. However, existing agents lack an effective experience reuse approach to leverage historical completed tasks. In this paper, we propose a novel experience reu…
Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools…
This study investigates the structured generation capabilities of large language models (LLMs), focusing on producing valid JSON outputs against a given schema. Despite the widespread use of JSON in integrating language models with programs, there is a lack of comprehensive analysis and benchmarking…
Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive…
Supernumerary Robotic Limbs (SRLs) can assist human motions by providing extra degrees of freedom (DoFs) and body support. The extra DoFs lead to larger design space in structure and control policies, which is complex and time-consuming with the traditional manual design process. In this pilot study
Hallucination remains a significant challenge in Large Vision-Language Models (LVLMs). To alleviate this issue, some methods, known as contrastive decoding, induce hallucinations by manually disturbing the raw vision or instruction inputs and then mitigate them by contrasting the outputs of the orig…
Offline reinforcement learning is widely applied in multiple fields due to its advantages in efficiency and risk control. However, a major problem it faces is the distribution shift between offline datasets and online environments. This mismatch leads to out-of-distribution (OOD) state-action pairs…
Recent advancements in large language models (LLMs) have driven a revolutionary paradigm shift in process automation from Robotic Process Automation to Agentic Process Automation by automating the workflow orchestration procedure based on LLMs. However, existing LLMs (even the advanced OpenAI GPT-4o…
The probability prediction of multivariate time series is a notoriously challenging but practical task. This research proposes to condense high-dimensional multivariate time series forecasting into a problem of latent space time series generation, to improve the expressiveness of each timestamp and…
Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the domain of code documentation generation remains underexplored. To this end, we introduce RepoAgent, a large language mode…
The superior generation capabilities of Denoised Diffusion Probabilistic Models (DDPMs) have been effectively showcased across a multitude of domains. Recently, the application of DDPMs has extended to time series generation tasks, where they have significantly outperformed other deep generative mod…
Objects of daily life are designed to suit the human hand. Without major modifications to these objects and our environments, robots will need end-effectors with human hand-like configuration and dexterity to efficiently operate on them. Tight integration of tactile and proprioceptive sensors are al…
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents struggle with seeking clarification and grasping precise use…
Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs. Motivated by the observation, in this paper, we study the problem of re-parameterizing and fine-tuning PLMs from a new perspective: Discovery of…
Robot hand is essential for a fully functional robot and designing a good robot hand is a sophisticated job that challenges the designer’s knowledge and experience. This paper presents a computational framework for automatic optimal robot hand design based on reinforcement learning (RL), which consi…
Recently, the relationship among individual pedestrian images and the relationship among pairwise pedestrian images have become attractive for person re-identification (re-ID) as they effectively improve the ability of feature representation. In this paper, we propose a novel method named Hybrid Rel…
Recently, some methods have focused on learning local relation among parts of pedestrian images for person re-identification (Re-ID), as it offers powerful representation capabilities. However, they only provide the intra-local relation among parts within single pedestrian image and ignore the inter…
Having the merits of chemical inertness and immunity to electromagnetic interference, light weight, small size, and softness, optical waveguides have attracted much attention in making tactile sensors recently. This paper presents a new design of waveguide using two layers of cores, one of which has…
A deep understanding of the movement mechanism of the human fingers is essential for achieving a human-like actuation mechanism for anthropomorphic robotic hands. After carefully analyzing a set of anatomical theories of human fingers, we propose a novel and more reasonable actuation mechanism of th