12 papers
JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments
Zhixi Cai, Fucai Ke, Sukai Huang +4
In complex embodied visual reasoning scenarios, an agent often has only a limited field of view, and the evidence needed to answer a question may be distributed across time, viewpo…
E-Orch: Towards Effective, Efficient, and Extensible Agentic Orchestration with Reinforcement Learning
Junnan Liu, Linhao Luo, Thuy-Trang Vu +1
Agentic orchestration enables multiple autonomous agents to solve complex tasks through adaptive decomposition, delegation, and execution. However, existing orchestrators often rel…
What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variatio…
Coordinated Scheduling for MoE LLM Serving
Yifan Sun, Zhexiang Zhang, Jiantong Jiang +5
Serving Mixture-of-Experts (MoE) large language models (LLMs) is challenging because dynamic request workloads interact with sparse expert routing, creating both data-parallel (DP)…
MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models
Manh Luong, Tamas Abraham, Junae Kim +6
Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text. We introduce MCBench,…
ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation
Akide Liu, Jinbo Xing, Chaojie Mao +8
Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challenge: single-shot extrapolation p…
AIPO: Learning to Reason from Active Interaction
Junnan Liu, Linhao Luo, Thuy-Trang Vu +1
Recent advances in LLMs have demonstrated strong reasoning capabilities, largely stimulated by RLVR. However, the exploration of existing RLVR algorithms remains largely constraine…
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction…
RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving
Hossein Hosseini Kasnavieh, Gholamreza Haffari, Christopher Leckie +1
Multi-model LLM routing has emerged as an effective approach for reducing serving cost and latency while maintaining output quality by assigning each prompt to an appropriate model…
VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations
Fucai Ke, Zhixi Cai, Boying Li +6
Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely fo…
CoV: Chain-of-View Prompting for Spatial Reasoning
Haoyu Zhao, Akide Liu, Zeyu Zhang +5
Embodied question answering (EQA) in 3D environments often requires collecting context that is distributed across multiple viewpoints and partially occluded. However, most recent v…
MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations
Gia-Bao Dinh Ho, Chang Wei Tan, Zahra Zamanzadeh Darban +3
Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences.…