13 accepted papers
Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inference-time techniques, including Chain/Tree/Graph-of-Thought(s), successfully improve the performance, as they are fairly c…
Policy exploration is critical in reinforcement learning (RL), where existing approaches include $\epsilon$-greedy, Gaussian process, etc. However, these approaches utilize preset stochastic processes and are indiscriminately applied in all kinds of RL tasks without considering task-specific feature…
Accurately estimating high-resolution carbon emissions is crucial for effective emission governance and mitigation planning. While conventional methods for precise carbon accounting are hindered by substantial data collection efforts, the rise of open data and advanced learning techniques offers a p
Efficient key-value (KV) cache compression is critical for scaling transformer-based Large Language Models (LLMs) in long sequences and resource-limited settings. Existing methods evict tokens based on their positions or importance, but position-based strategies can miss crucial information outside
Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long texts. Most KV cache compression methods evict the unimportant K…
Accounting for over 20% of the total carbon emissions, the precise estimation of on-road transportation carbon emissions is crucial for carbon emission monitoring and efficient mitigation policy formulation. However, existing estimation methods typically depend on hard-to-collect individual statisti…
The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial information about a token can be derived from its neighbors.…
Citation networks are critical infrastructures of modern science, serving as intricate webs of past literature and enabling researchers to navigate the knowledge production system. To mine information hiding in the link space of such networks, predicting which previous papers (candidates) will a new…
Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing multi-class objects and dense objects with occlusions remain…
Data with missing values is ubiquitous in many applications. Recent years have witnessed increasing attention on prediction with only incomplete data consisting of observed features and a mask that indicates the missing pattern. Existing methods assume that the training and testing distributions are…
Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end goal of OPE is to compare two or multiple candidate policies a…
Deep reinforcement learning (DRL) is able to learn control policies for many complicated tasks, but it's power has not been unleashed to handle multi-agent circumstances. Independent learning, where each agent treats others as part of the environment and learns its own policy without considering oth…
This work addresses a multi-agent cooperative navigation problem that multiple agents work together in an unknown environment in order to reach different targets without collision and minimize the maximum navigation time they spend. Typical reinforcement learning-based solutions directly model the c…