arXiv subjects

Xuanxuan Liu

Publications and source records attributed to Xuanxuan Liu.

3 recordsLinked to original sources

arXiv2026

Limitations of Best-of-Both-Worlds Solutions in Approval-Based Multiwinner Elections

We study the best-of-both-worlds fairness in approval-based multi-winner elections, asking whether ex-ante guarantees for a fractional outcome can be implemented while every realized committee satisfies an ex-post representation axiom. Recent work has shown that several ex-ante proportionality guarantees can be achieved together with strong ex-post representation axioms. We first prove that ex-ante weak Pareto optimality (weak PO), which requires that no other fractional outcome makes every voter strictly better off, is incompatible with ex-post justified representation (JR). Since fractional core stability implies weak PO, this also rules out the possibility of combining ex-ante fractional core, a central fairness notion for fractional committees, with ex-post JR. We further show that ex-ante AJR is incompatible with ex-post JR, even though AJR is a much stronger average-representation analogue of JR. On the positive side, we show that the fractional ex-ante side itself remains highly compatible: several natural ex-ante representation guarantees can be satisfied simultaneously, including fractional core, group-resource proportionality, AJR (as well as its strict strengthening AJR+), and Pareto-optimality. Hence, highly fair fractional committees may exist even when they cannot be implemented by randomization over JR committees. Our results separate fractional representation from best-of-both-worlds implementability and identify fundamental limitations of fair randomized committee selection.

cs.GT↗

arXiv2026

GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows

The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows. However, current tool-use benchmarks remain misaligned with real-world requirements, relying on AI-generated queries, dummy tools, and limited system-level coordination. To address this, we propose GTA-2, a hierarchical benchmark for General Tool Agents (GTA) spanning atomic tool use and open-ended workflows. Built on real-world authenticity, it leverages real user queries, deployed tools, and multimodal contexts. (i) GTA-Atomic, inherited from our prior GTA benchmark, evaluates short-horizon, closed-ended tool-use precision. (ii) GTA-Workflow introduces long-horizon, open-ended tasks for realistic end-to-end completion. To evaluate open-ended deliverables, we propose a recursive checkpoint-based evaluation mechanism that decomposes objectives into verifiable sub-goals, enabling unified evaluation of both model capabilities and agent execution frameworks (i.e., execution harnesses). Experiments reveal a pronounced capability cliff: while frontier models already struggle on atomic tasks (below 50%), they largely fail on workflows, with top models achieving only 14.39% success. Further analysis shows that checkpoint-guided feedback improves performance, while advanced frameworks such as Manus and OpenClaw substantially enhance workflow completion, highlighting the importance of execution harness design beyond the underlying model capacity. These findings provide guidance for developing reliable personal and professional assistants. Dataset and code will be available at https://github.com/open-compass/GTA.

cs.CL↗

arXiv2025

Generative AI for Film Creation: A Survey of Recent Advances

Generative AI (GenAI) is transforming filmmaking, equipping artists with tools like text-to-image and image-to-video diffusion, neural radiance fields, avatar generation, and 3D synthesis. This paper examines the adoption of these technologies in filmmaking, analyzing workflows from recent AI-driven films to understand how GenAI contributes to character creation, aesthetic styling, and narration. We explore key strategies for maintaining character consistency, achieving stylistic coherence, and ensuring motion continuity. Additionally, we highlight emerging trends such as the growing use of 3D generation and the integration of real footage with AI-generated elements. Beyond technical advancements, we examine how GenAI is enabling new artistic expressions, from generating hard-to-shoot footage to dreamlike diffusion-based morphing effects, abstract visuals, and unworldly objects. We also gather artists' feedback on challenges and desired improvements, including consistency, controllability, fine-grained editing, and motion refinement. Our study provides insights into the evolving intersection of AI and filmmaking, offering a roadmap for researchers and artists navigating this rapidly expanding field.

cs.CV↗