collaborators

8 papers

math-ph2026

Counterexamples to the total-current Hohenberg-Kohn conjecture

Andre Laestadius, Mihály A. Csirik

The total-current Hohenberg-Kohn conjecture asserts that the ground-state particle density and total current determine the scalar potential up to an additive constant and the vecto…

cs.CL2026

Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability

Yu Mao, Lei Yu, Zining Zhu +6

We connect the spurious-reward paradox to a model's reachability and propose random-reward reinforcement learning (RL) as a useful tool for the probing enterprise, addressing a dec…

cs.CL2026

MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines

Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5

This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers…

cs.CV2026

Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing

Lecheng Yan, Yichong Zhang, Xiantao Xu +12

Long-form video editing over heterogeneous footage requires agents to coordinate source selection, multimodal analysis, timeline construction, narration and subtitle alignment, ren…

cs.AI2026

Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents

Weidi Luo, Qiming Zhang, Yihao Quan +5

Command-Line Interface (CLI) agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risk…

cs.CL2026

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery

Alireza Bayat Makou, Jingcheng Niu, Subhabrata Dutta +1

Circuit discovery methods identify subgraphs that explain model behaviors, and structural differences between discovered circuits are commonly interpreted as evidence of distinct m…

cs.CL2026

All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs

Xi Chen, Mingyu Jin, Jingcheng Niu +7

In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional An…

cs.IR2026

RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm

Jiahe Liu, Qinkai Yu, Jingcheng Niu +5

Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g., private databases, global c…