Researcher profile

Haolin Liu

Haolin Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computation and Language Computer Vision Artificial Intelligence Machine Learning Emerging Technologies Human-Computer Interaction

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

7works

0followers

6topics

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

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking. To overcome this, we introduce G-Zero, a verifier-free, co-evolutionary framework for autonomous self-improvement. Our core innovation is Hint-$δ$, an intrinsic reward that quantifies the predictive shift between a Generator model's unassisted response and its response conditioned on a self-generated hint. Using this signal, a Proposer model is trained via GRPO to continuously target the Generator's blind spots by synthesizing challenging queries and informative hints. The Generator is concurrently optimized via DPO to internalize these hint-guided improvements. Theoretically, we prove a best-iterate suboptimality guarantee for an idealized standard-DPO version of G-Zero, provided that the Proposer induces sufficient exploration coverage and the data filteration keeps pseudo-label score noise low. By deriving supervision entirely from internal distributional dynamics, G-Zero bypasses the capability ceilings of external judges, providing a scalable, robust pathway for continuous LLM self-evolution across unverifiable domains.

preprint2026arXiv

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually design reasoning patterns and tune heuristics by intuition, leaving much of the computation-allocation space unexplored. We propose an environment-driven framework, AutoTTS, that changes what researchers design: from individual TTS heuristics to environments where TTS strategies can be discovered automatically. The key to AutoTTS lies in environment construction: the discovery environment must make the control space tractable and provide cheap, frequent feedback for TTS search. As a concrete instantiation, we formulate width--depth TTS as controller synthesis over pre-collected reasoning trajectories and probe signals, where controllers decide when to branch, continue, probe, prune, or stop and can be evaluated cheaply without repeated LLM calls. We further introduce beta parameterization to make the search tractable and fine-grained execution trace feedback to improve discovery efficiency by helping the agent diagnose why a TTS program fails. Experiments on mathematical reasoning benchmarks show that the discovered strategies improve the overall accuracy--cost tradeoff over strong manually designed baselines. The discovered strategies generalize to held-out benchmarks and model scales, while the entire discovery costs only $39.9 and 160 minutes. Our data, and code will be open-source at https://github.com/zhengkid/AutoTTS.

preprint2026arXiv

Reinforcing Multimodal Reasoning Against Visual Degradation

Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-world visual degradations such as blur, compression artifacts, and low-resolution scans. Prior robustness techniques from vision and deep RL rely on static data augmentation or value-based regularization, neither of which transfers cleanly to critic-free RL fine-tuning of autoregressive MLLMs. Reinforcing reasoning against such corruptions is non-trivial: naively injecting degraded views during rollout induces reward poisoning, where perceptual occlusions trigger hallucinated trajectories and destabilize optimization. We propose ROMA, an RL fine-tuning framework that modifies the optimization dynamics to reinforce reasoning against visual degradation while preserving clean-input performance. A dual-forward-pass strategy uses teacher forcing to evaluate corrupted views against clean-image trajectories, avoiding new rollouts on degraded inputs. For distributional consistency, we apply a token-level surrogate KL penalty against the worst-case augmentation; to prevent policy collapse under regularization, an auxiliary policy gradient loss anchored to clean-image advantages preserves a reliable reward signal; and to avoid systematically incorrect invariance, correctness-conditioned regularization restricts enforcement to successful trajectories. On Qwen3-VL 4B/8B across seven multimodal reasoning benchmarks, our method improves robustness by +2.4% on seen and +2.3% on unseen corruptions over GRPO while matching clean accuracy.

preprint2026arXiv

RelayLLM: Efficient Reasoning via Collaborative Decoding

Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack the necessary reasoning capacity. Existing collaborative approaches, such as cascading or routing, operate at a coarse granularity by offloading entire queries to LLMs, resulting in significant computational waste when the SLM is capable of handling the majority of reasoning steps. To address this, we propose RelayLLM, a novel framework for efficient reasoning via token-level collaborative decoding. Unlike routers, RelayLLM empowers the SLM to act as an active controller that dynamically invokes the LLM only for critical tokens via a special command, effectively "relaying" the generation process. We introduce a two-stage training framework, including warm-up and Group Relative Policy Optimization (GRPO) to teach the model to balance independence with strategic help-seeking. Empirical results across six benchmarks demonstrate that RelayLLM achieves an average accuracy of 49.52%, effectively bridging the performance gap between the two models. Notably, this is achieved by invoking the LLM for only 1.07% of the total generated tokens, offering a 98.2% cost reduction compared to performance-matched random routers.

preprint2022arXiv

TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes

Many basic indoor activities such as eating or writing are always conducted upon different tabletops (e.g., coffee tables, writing desks). It is indispensable to understanding tabletop scenes in 3D indoor scene parsing applications. Unfortunately, it is hard to meet this demand by directly deploying data-driven algorithms, since 3D tabletop scenes are rarely available in current datasets. To remedy this defect, we introduce TO-Scene, a large-scale dataset focusing on tabletop scenes, which contains 20,740 scenes with three variants. To acquire the data, we design an efficient and scalable framework, where a crowdsourcing UI is developed to transfer CAD objects from ModelNet and ShapeNet onto tables from ScanNet, then the output tabletop scenes are simulated into real scans and annotated automatically. Further, a tabletop-aware learning strategy is proposed for better perceiving the small-sized tabletop instances. Notably, we also provide a real scanned test set TO-Real to verify the practical value of TO-Scene. Experiments show that the algorithms trained on TO-Scene indeed work on the realistic test data, and our proposed tabletop-aware learning strategy greatly improves the state-of-the-art results on both 3D semantic segmentation and object detection tasks. Dataset and code are available at https://github.com/GAP-LAB-CUHK-SZ/TO-Scene.

preprint2022arXiv

Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes

We present a new framework to reconstruct holistic 3D indoor scenes including both room background and indoor objects from single-view images. Existing methods can only produce 3D shapes of indoor objects with limited geometry quality because of the heavy occlusion of indoor scenes. To solve this, we propose an instance-aligned implicit function (InstPIFu) for detailed object reconstruction. Combining with instance-aligned attention module, our method is empowered to decouple mixed local features toward the occluded instances. Additionally, unlike previous methods that simply represents the room background as a 3D bounding box, depth map or a set of planes, we recover the fine geometry of the background via implicit representation. Extensive experiments on the SUN RGB-D, Pix3D, 3D-FUTURE, and 3D-FRONT datasets demonstrate that our method outperforms existing approaches in both background and foreground object reconstruction. Our code and model will be made publicly available.

preprint2020arXiv

SimuLearn: Fast and Accurate Simulator to Support Morphing Materials Design and Workflows

Morphing materials allow us to create new modalities of interaction and fabrication by leveraging dynamic behaviors of materials. Yet, despite the ongoing rapid growth of computational tools within this realm, current developments are bottlenecked by the lack of an effective simulation method. As a result, existing design tools must trade-off between speed and accuracy to support a real-time interactive design scenario. In response, we introduce SimuLearn, a data-driven method that combines finite element analysis and machine learning to create real-time (0.61 seconds) and truthful (97% accuracy) morphing material simulators. We use mesh-like 4D printed structures to contextualize this method and prototype design tools to exemplify the design workflows and spaces enabled by a fast and accurate simulation method. Situating this work among existing literature, we believe SimuLearn is a timely addition to the HCI CAD toolbox that can enable the proliferation of morphing materials.

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