Search Results for author:
Found 29 papers, 20 papers with code
SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions.
TARS: Traffic-Aware Radar Scene Flow Estimation
Scene flow provides crucial motion information for autonomous driving.
LocAgent: Graph-Guided LLM Agents for Code Localization
By parsing codebases into directed heterogeneous graphs, LocAgent creates a lightweight representation that captures code structures (files, classes, functions) and their dependencies (imports, invocations, inheritance), enabling LLM agents to effectively search and locate relevant entities through powerful multi-hop reasoning.
PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation
Personalized large language models (LLMs) aim to tailor their outputs to user preferences.
Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties
Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications.
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Machine writing with large language models often relies on retrieval-augmented generation.
WebWalker: Benchmarking LLMs in Web Traversal
Extensive experimental results show that WebWalkerQA is challenging and demonstrates the effectiveness of RAG combined with WebWalker, through the horizontal and vertical integration in real-world scenarios.
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation
Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation.
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i. e., math, coding, commonsense reasoning).
Long-Sequence Recommendation Models Need Decoupled Embeddings
In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes.
AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment
Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent and the need for historical context.
Symbolic Learning Enables Self-Evolving Agents
In this work, we introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own in a data-centric way using symbolic optimizers.
SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
However, such methods introduce significant inference latency due to the systematic exploration and evaluation of multiple thought paths.
SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data
Radar-based perception has gained increasing attention in autonomous driving, yet the inherent sparsity of radars poses challenges.
iVideoGPT: Interactive VideoGPTs are Scalable World Models
This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction.
CompilerDream: Learning a Compiler World Model for General Code Optimization
Effective code optimization in compilers is crucial for computer and software engineering.
Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment
Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases.
STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models
For poor model calibration, we incorporate the regularization method during LoRA training to keep the model from being over-confident, and the Monte-Carlo dropout mechanism is employed to enhance the uncertainty estimation.
DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
However, most of the present debiasing methods focus on single-variable causal inference, which is not suitable for ABSA with two input variables (the target aspect and the review).
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Weaver: Foundation Models for Creative Writing
Weaver is pre-trained on a carefully selected corpus that focuses on improving the writing capabilities of large language models.
Constituency Parsing using LLMs
Constituency parsing is a fundamental yet unsolved natural language processing task.
HarmonyDream: Task Harmonization Inside World Models
Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward modeling.
Ranked #4 on
Atari Games 100k
on Atari 100k
Agents: An Open-source Framework for Autonomous Language Agents
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces.
Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes.
CLIPood: Generalizing CLIP to Out-of-Distributions
This paper aims at generalizing CLIP to out-of-distribution test data on downstream tasks.
Out-of-Dynamics Imitation Learning from Multimodal Demonstrations
Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator.
Real-Time And Robust 3D Object Detection with Roadside LiDARs
This work aims to address the challenges in autonomous driving by focusing on the 3D perception of the environment using roadside LiDARs.
Flowformer: Linearizing Transformers with Conservation Flows
By respectively conserving the incoming flow of sinks for source competition and the outgoing flow of sources for sink allocation, Flow-Attention inherently generates informative attentions without using specific inductive biases.
Ranked #4 on
D4RL
on D4RL
Supported Policy Optimization for Offline Reinforcement Learning
Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy.
