Researcher profile

Hang Yuan

Hang Yuan contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computation and Language Artificial Intelligence Computer Vision cond-mat.soft Robotics cond-mat.mtrl-sci physics.flu-dyn

Trust snapshot

Quick read

Trust 19 - UnverifiedVerification L1Unclaimed author

5works

0followers

7topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

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

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

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.

preprint2026arXiv

Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding

Discrete diffusion language models improve generation efficiency through parallel token prediction, but standard $X_0$ prediction methods introduce factorization errors by approximating the clean token posterior with independent token-wise distributions. This paper proposes Factorization-Error-Free Discrete Diffusion Language Modeling (FeF-DLLM), which replaces independent clean-token prediction with an exact prefix-conditioned factorization of the clean posterior to better preserve token dependencies. To reduce the sequential cost introduced by prefix conditioning, FeF-DLLM further incorporates speculative decoding within diffusion denoising, accelerating inference while maintaining the parallel prediction and re-masking properties of DLLMs. Theoretically, we prove that FeF-DLLM generates from the true joint distribution and derive its expected acceleration ratio. Experiments on GSM8K, MATH, HumanEval, and MBPP demonstrate that our method improves accuracy by an average of 5.04 percentage points while achieving an average inference speedup of $3.86\times$.

preprint2026arXiv

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines

preprint2026arXiv

PhysBrain 1.0 Technical Report

Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding. PhysBrain 1.0 studies a complementary route: converting large-scale human egocentric video into structured physical commonsense supervision before robot adaptation. Our data engine extracts scene elements, spatial dynamics, action execution, and depth-aware relations, then turns them into question-answer supervision for training PhysBrain VLMs. The resulting physical priors are further transferred to VLA policies through a capability-preserving and language-sensitive adaptation design. Across multimodal QA benchmarks and embodied control benchmarks, including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa, PhysBrain 1.0 achieves SOTA results and shows especially strong out-of-domain performance on SimplerEnv. These results suggest that scaling physical commonsense from human interaction video can provide an effective bridge from multimodal understanding to robot action.

preprint2022arXiv

Stokesian Dynamics with odd viscosity

Stokesian Dynamics is a well-established computational method for simulating dynamics of many particles suspended in a conventional passive fluid medium. Active fluids composed of self-propelling particles with broken time reversal symmetry permit the emergence of a so-called odd viscosity. In this work, we extended the conventional Stokesian Dynamics formalism to incorporate the additional hydrodynamic effects due to odd viscosity, which enables simulating collective behaviors of many particles suspended in an active fluid medium with both even viscosity and odd viscosity.

preprint2021arXiv

Polar state memory in active fluids

Spontaneous emergence of correlated states such as flocks and vortices are prime examples of remarkable collective dynamics and self-organization observed in active matter. The formation of globally correlated polar states in geometrically confined systems proceeds through the emergence of a macroscopic steadily rotating vortex that spontaneously selects a clockwise or counterclockwise global chiral state. Here, we reveal that a global vortex formed by colloidal rollers exhibits state memory. The information remains stored even when the energy injection is ceased and the activity is terminated. We show that a subsequent formation of the collective states upon re-energizing the system is not random. We combine experiments and simulations to elucidate how a combination of hydrodynamic and electrostatic interactions leads to hidden asymmetries in the local particle positional order encoding the chiral state of the system. The stored information can be accessed and exploited to systematically command subsequent polar states of active liquid through temporal control of the activity. With the chirality of the emergent collective states controlled on-demand, active liquids offer new possibilities for flow manipulation, transport, and mixing at the microscale.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint