BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Shunyu Yao

Shunyu Yao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and LanguageArtificial Intelligencemath.COComputer Visioncond-mat.str-elDiscrete Mathematicshep-exhep-thMachine Learningmath.OC

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

9 published item(s)

preprint2026arXiv

CL-bench Life: Can Language Models Learn from Real-Life Context?

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

GPS-Synchronized Monitoring of Core-collapse Supernova Bursts with PandaX-4T via Coherent Elastic Neutrino Nuclear Scattering

The landmark detection of neutrinos from SN1987A marked the dawn of neutrino astrophysics. The neutrino burst provided essential insights into fundamental properties of neutrinos, and served as key probes of stellar evolution and supernova dynamics. The recent advancement in coherent elastic neutrino-nucleus scattering enables the detection of core-collapse supernova burst neutrinos using tonne-scale liquid xenon detectors originally designed for dark matter direct detection. Leveraging this capability, we developed and deployed an online supernova monitoring system for the PandaX-4T experiment. This system features a GPS module with millisecond-level timing precision, a low false-alarm rate, and high sensitivity to galactic core-collapse supernova explosion events. The methodology is robust, directly scalable, and planned for implementation in the next-generation PandaX-20T experiment.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering

While recent advances in deep neural networks have made it possible to render high-quality images, generating photo-realistic and personalized talking head remains challenging. With given audio, the key to tackling this task is synchronizing lip movement and simultaneously generating personalized attributes like head movement and eye blink. In this work, we observe that the input audio is highly correlated to lip motion while less correlated to other personalized attributes (e.g., head movements). Inspired by this, we propose a novel framework based on neural radiance field to pursue high-fidelity and personalized talking head generation. Specifically, neural radiance field takes lip movements features and personalized attributes as two disentangled conditions, where lip movements are directly predicted from the audio inputs to achieve lip-synchronized generation. In the meanwhile, personalized attributes are sampled from a probabilistic model, where we design a Transformer-based variational autoencoder sampled from Gaussian Process to learn plausible and natural-looking head pose and eye blink. Experiments on several benchmarks demonstrate that our method achieves significantly better results than state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Linking Emergent and Natural Languages via Corpus Transfer

The study of language emergence aims to understand how human languages are shaped by perceptual grounding and communicative intent. Computational approaches to emergent communication (EC) predominantly consider referential games in limited domains and analyze the learned protocol within the game framework. As a result, it remains unclear how the emergent languages from these settings connect to natural languages or provide benefits in real-world language processing tasks, where statistical models trained on large text corpora dominate. In this work, we propose a novel way to establish such a link by corpus transfer, i.e. pretraining on a corpus of emergent language for downstream natural language tasks, which is in contrast to prior work that directly transfers speaker and listener parameters. Our approach showcases non-trivial transfer benefits for two different tasks -- language modeling and image captioning. For example, in a low-resource setup (modeling 2 million natural language tokens), pre-training on an emergent language corpus with just 2 million tokens reduces model perplexity by $24.6\%$ on average across ten natural languages. We also introduce a novel metric to predict the transferability of an emergent language by translating emergent messages to natural language captions grounded on the same images. We find that our translation-based metric highly correlates with the downstream performance on modeling natural languages (for instance $ρ=0.83$ on Hebrew), while topographic similarity, a popular metric in previous work, shows surprisingly low correlation ($ρ=0.003$), hinting that simple properties like attribute disentanglement from synthetic domains might not capture the full complexities of natural language. Our findings also indicate potential benefits of moving language emergence forward with natural language resources and models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-Stage Episodic Control for Strategic Exploration in Text Games

Text adventure games present unique challenges to reinforcement learning methods due to their combinatorially large action spaces and sparse rewards. The interplay of these two factors is particularly demanding because large action spaces require extensive exploration, while sparse rewards provide limited feedback. This work proposes to tackle the explore-vs-exploit dilemma using a multi-stage approach that explicitly disentangles these two strategies within each episode. Our algorithm, called eXploit-Then-eXplore (XTX), begins each episode using an exploitation policy that imitates a set of promising trajectories from the past, and then switches over to an exploration policy aimed at discovering novel actions that lead to unseen state spaces. This policy decomposition allows us to combine global decisions about which parts of the game space to return to with curiosity-based local exploration in that space, motivated by how a human may approach these games. Our method significantly outperforms prior approaches by 27% and 11% average normalized score over 12 games from the Jericho benchmark (Hausknecht et al., 2020) in both deterministic and stochastic settings, respectively. On the game of Zork1, in particular, XTX obtains a score of 103, more than a 2x improvement over prior methods, and pushes past several known bottlenecks in the game that have plagued previous state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Subleading Weingartens

Haar integrals over the unitary group contain subleading terms that are needed for unitarity. We study analogous effects in the time evolution operators of JT gravity and Brownian SYK. In JT gravity with bulk matter we find an explanation for the first subleading terms, and in Brownian SYK we find configurations that can explain the full series. An important role is played by slightly off-shell modes that are exponentially amplified by chaos.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

TVShowGuess: Character Comprehension in Stories as Speaker Guessing

We propose a new task for assessing machines' skills of understanding fictional characters in narrative stories. The task, TVShowGuess, builds on the scripts of TV series and takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues. Our human study supports that this form of task covers comprehension of multiple types of character persona, including understanding characters' personalities, facts and memories of personal experience, which are well aligned with the psychological and literary theories about the theory of mind (ToM) of human beings on understanding fictional characters during reading. We further propose new model architectures to support the contextualized encoding of long scene texts. Experiments show that our proposed approaches significantly outperform baselines, yet still largely lag behind the (nearly perfect) human performance. Our work serves as a first step toward the goal of narrative character comprehension.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Integer Linear Programming Formulations for Double Roman Domination Problem

For a graph $G= (V,E)$, a double Roman dominating function (DRDF) is a function $f : V \to \{0,1,2,3\}$ having the property that if $f (v) = 0$, then vertex $v$ must have at least two neighbors assigned $2$ under $f$ or {at least} one neighbor $u$ with $f (u) = 3$, and if $f (v) = 1$, then vertex $v$ must have at least one neighbor $u$ with $f (u) \ge 2$. In this paper, we consider the double Roman domination problem, which is an optimization problem of finding the DRDF $f$ such that $\sum_{v\in V} f (v)$ is minimum. We propose {five integer linear programming (ILP) formulations and one mixed integer linear programming formulation with polynomial number of constraints for this problem. Some additional valid inequalities and bounds are also proposed for some of these formulations.} Further, we prove that {the first four models indeed solve the double Roman domination problem, and the last two models} are equivalent to the others regardless of the variable relaxation or usage of a smaller number of constraints and variables. Additionally, we use one ILP formulation to give an $H(2(Δ+1))$-approximation algorithm. All proposed formulations and approximation algorithm are evaluated on randomly generated graphs to compare the performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

k-Ary spanning trees contained in tournaments

A rooted tree is called a $k$-ary tree, if all non-leaf vertices have exactly $k$ children, except possibly one non-leaf vertex has at most $k-1$ children. Denote by $h(k)$ the minimum integer such that every tournament of order at least $h(k)$ contains a $k$-ary spanning tree. It is well-known that every tournament contains a Hamiltonian path, which implies that $h(1)=1$. Lu et al. [J. Graph Theory {\bf 30}(1999) 167--176] proved the existence of $h(k)$, and showed that $h(2)=4$ and $h(3)=8$. The exact values of $h(k)$ remain unknown for $k\geq 4$. A result of Erdős on the domination number of tournaments implies $h(k)=Ω(k\log k)$. In this paper, we prove that $h(4)=10$ and $h(5)\geq13$.

0 citations0 reviewsNo code linkedOpen access