Searcharxiv⌕ Search

arXiv subjects

Yuchen Wang

Publications and source records attributed to Yuchen Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Signature-Guided Capacity Occupancy for Dense Expert Merging

Dense expert merging combines domain-specialized language models into one single checkpoint, typically by admitting task-vector support in weight space. However, this admission is governed by three decisions that existing methods answer only partially: where to open layer capacity from cross-expert conflict, who should occupy that capacity based on domain demand, and how to admit the resulting support without relying on costly recipe search. To tackle these issues, we propose SigMerge (Signature-Guided Capacity Occupancy), a structured capacity assignment framework for dense expert merging. Starting from a dense base merge, conflict signatures set each layer's capacity from cross-expert conflict, positive base-merge deficits set each domain's share of that capacity, and a sequential occupancy rule admits each expert delta up to the resulting layer-domain budget. Across 21 paired settings spanning seven dense base merges and three model pools, SigMerge improves every one (by 15.0% on average) and achieves the best average rank (1.67) among six merging methods, outperforming three categories of merging baselines.

cs.AI↗
arXiv2026

JADE-GS: Joint Allocation of Deblurring Evidence for Event-Assisted 3D Gaussian Splatting

Neural radiance fields and 3D Gaussian Splatting assume that each training image is a sharp and geometrically consistent observation of the scene. Motion blur violates this assumption because a single exposure integrates a continuous range of camera poses. Exposure integration also removes the temporal information needed to recover the corresponding sharp observation. Event cameras preserve this information at microsecond resolution and therefore provide a natural complement to conventional images. Existing event-assisted reconstruction methods predominantly obtain image supervision through analytical inversion of the Event Double Integral. Learned restoration from frames and events offers a second prior. Although weaker when used alone, it fails in different regions and provides complementary evidence. We present JADE-GS, which formulates the combination of these priors as spatial evidence allocation. A lightweight Spatial Prior Router predicts a pixelwise allocation using only the blurry frame and event stream, then fuses the two fixed restorations into an additional supervision target. The router is trained without a sharp reference using consistency with the scene under reconstruction and the measured exposure, and is removed after optimization. Experiments show that JADE-GS achieves leading perceptual quality on both benchmarks, attains the best fidelity on the real benchmark, and remains competitive on the synthetic one. It requires substantially lower training overhead than diffusion-based alternatives and preserves native 3DGS rendering with no generative decoding at inference.

cs.CV↗
arXiv2026

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models

Recent multimodal large language models (MLLMs), such as Qwen2.5-VL and InternVL3, generate large numbers of vision tokens for high-resolution inputs, leading to substantial computational cost. Existing vision token pruning methods either depend on cross-modal attention and cannot prune before the prefill stage, or rely on diversity estimation with high computational overhead. We observe that attention scores from both vision and text tokens peak at modality separator tokens, suggesting that these separators bridge the two modalities. Based on this observation, we propose SepPrune, an efficient, training-free, plug-and-play pruning method that uses the separator token as a unified query to rank and select informative vision tokens. SepPrune reuses the LLM's built-in projection parameters and requires no architectural changes. Experiments on Qwen2.5-VL-7B show that SepPrune achieves state-of-the-art performance, retaining 96.3% of the original accuracy while removing 80.2% of vision tokens.

cs.CV↗
arXiv2026

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models

On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories generated by the student. However, existing methods often rely on verified solution traces, explanations generated by external models, or manually localized visual evidence, which limits their scalable application to multimodal large language models. To address this issue, we exploit the information gap between high- and low-resolution views of the same image and propose RP-OPSD (Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models). During training, the student policy generates on-policy trajectories from images at one-quarter of the original resolution, while the teacher policy provides supervision using the original-resolution images. By minimizing the divergence between their output distributions along the student trajectories, the student learns the predictive behavior of the teacher under high-resolution inputs, thereby strengthening its low-resolution capability and transferring the learned improvement to original-resolution inference. RP-OPSD requires neither additional human annotations nor external models to generate solution traces but only image--question pairs. Experiments on Qwen3.5-9B show that RP-OPSD achieves a 5.45\% relative improvement in average performance at the original resolution and a $1.78\times$ training speedup over OPSD. These results demonstrate that resolution differences can serve as a simple and scalable source of privileged information, providing an effective and efficient approach to on-policy self-distillation for multimodal large language models.

cs.CV↗
arXiv2026

MFTune: An Efficient Multi-fidelity Framework for Spark SQL Configuration Tuning

Apache Spark SQL is a cornerstone of modern big data analytics.However,optimizing Spark SQL performance is challenging due to its vast configuration space and the prohibitive cost of evaluating massive workloads. Existing tuning methods predominantly rely on full-fidelity evaluations, which are extremely time-consuming,often leading to suboptimal performance within practical budgets.While multi-fidelity optimization offers a potential solution, directly applying standard techniques-such as data volume reduction or early stopping-proves ineffective for Spark SQL as they fail to preserve performance correlations or represent true system bottlenecks. To address these challenges, we propose MFTune, an efficient multi-fidelity framework that introduces a query-based fidelity partitioning strategy, utilizing representative SQL subsets to provide accurate, low-cost proxies. To navigate the huge search space, MFTune incorporates a density-based optimization mechanism for automated knob and range compression, alongside an adapted transfer learning approach and a two-phase warm start to further accelerate the tuning process. Experimental results on TPC-H and TPC-DS benchmarks demonstrate that MFTune significantly outperforms five state-of-the-art tuning methods, identifying superior configurations within practical time constraints.

cs.DB↗
arXiv2026

Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction

A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-language requirement specifications, with minimal or no manual redesign. In this setting, policy generation by AI agents can be a credible path when paired with a plant-aware validator (e.g., a digital twin) that can check generated candidate actions before execution. However, practical deployment is constrained by inference latency and compute footprint: large cloud-based models are often too slow, opaque, or data-sensitive for edge closed-loop use. This work investigates whether a compact Small Language Model (SLM) can be retrained for control reasoning and embedded in a validator-guided correction loop. We use a Qwen2.5-1.5B model aligned via Group Relative Policy Optimization (GRPO), combined with (i) an action agent, (ii) a symbolic/digital-twin-style validation layer, and (iii) a reprompting agent that iteratively steers outputs toward valid actions. In randomized thermal-control simulations (30 experiments with 500 steps each), the framework achieves 91.5% average action-alignment accuracy (86.3%--100% across cases) at 3.84\,s mean inference latency. Under symbolic re-mapping, it maintains a 95% in-range rate, indicating robust physical regulation despite reduced token-level agreement. These results support SLM+validator architectures as a practical path toward reconfigurable autonomous control at the edge.

cs.AI↗
arXiv2026

Large Photoelasticity in Topological Antiferromagnet Mn$_3$Sn Studied by Coherent Acoustic Phonon

We investigate the role of ultrafast strain on the electronic and optical responses in topological antiferromagnet Mn$_3$Sn thin films using near-infrared femtosecond pump-probe spectroscopy. Coherent acoustic phonons are generated and exhibit remarkably large oscillations in differential transmission exceeding 1% in amplitude. Our quantitative analysis reveals that Mn$_3$Sn possesses an unusually large near-infrared photoelastic coefficient, several times greater than those in conventional materials, indicating a remarkable sensitivity of the electronic states to lattice distortions. This work establishes a quantitative framework for understanding and utilizing strain-induced responses in Mn$_3$Sn, paving a foundation for exploring coupled electron-phonon-magnon dynamics for ultrafast straintronics.

cond-mat.mtrl-sci↗
arXiv2026

Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure

Automated research-idea generation systems built on large language models (LLMs) share a structural weakness: they reduce ideation to free-text recombination, random paper pairing, or embedding-similarity retrieval. The three approaches fail in the same way: each treats a paper as a flat object, a string or a vector, and so quotients away the typed problem-method-metric-claim arrows a researcher actually uses when reasoning about a cross-domain analogy. We recover the missing structure with the minimal piece of category theory that a typed graph alone does not provide: composition, together with identity arrows, which makes it possible to ask whether a proposed analogy preserves relation chains. Concretely, each paper $p$ is modelled as a small category $C_p$ whose objects are extracted typed research entities and whose morphisms are the relations the paper asserts; a cross-paper bridge from $p$ to $q$ is then a partial functor candidate $F: C_p -> C_q$ that preserves object kinds and covered relation classes. We instantiate the model as a three-layer algorithm: categorical signature clustering, a functor-preservation gate, and a six-axis LLM plausibility judge. Evaluated on a corpus of tens of thousands of full-text-parsed papers under four ablation conditions, the categorical gate filters cross-domain candidates at roughly a 17:1 ratio while the quantitative-falsifier rate of accepted ideas stays above 83% throughout; every rejected candidate is retained with its per-axis rationale, so the gate doubles as a logging layer rather than a silent filter.

cs.CL↗
arXiv2026

Quantum Mechanical Studies of Photodissociation Dynamics on Quantum Computers

Theoretical quantum dynamics calculations scale deeply with system size, rendering classical calculations intractable for complex systems. While quantum computing offers a natural solution, its application to nuclear quantum dynamics remains scarce. Here, we present a quantum algorithm to study photodissociation dynamics on quantum computers, benchmarked on the NOCl molecule. The wavefunction is propagated via a split-operator method, utilizing the Quantum Fourier Transform and unitary transformation matrix to switch representations. To impose outgoing boundary conditions on a truncated grid, we use a non-unitary absorbing potential propagator, implemented through a dilation scheme. The photodissociation cross section is calculated from the auto-correlation function, which is extracted using the Hadamard test. Our quantum computing results agree well with benchmarks under ideal conditions, and we further demonstrate that the algorithm is robust to noise and statistical sampling errors, indicating the promising application of noisy devices to quantum dynamics studies.

quant-ph↗
arXiv2026

MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exhibit degeneration of thought, where the LLM continues to repeat the same errors again and again even with the knowledge that its wrong. To address this problem, we instead introduce multi-agent with multi-persona debators as the method to generate reflections. Through out extensive experimentation, we've found that the leads to better diversity of in the reflections generated by the llm agent. We demonstrate an accuracy of 47% EM HotPot QA (question answering) and 82.7% on HumanEval (programming), both performances surpassing reflection with a single llm.

cs.AI↗
arXiv2026

Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation Learning

As live streaming services grow, many platforms offer short videos and live streams to meet diverse needs. Short videos carry substantial traffic and rich behavior signals, whereas live streaming is a core conversion scenario with sparse behavior data, making cold start severe. Transferring user interests from short videos to live streaming recommendation can alleviate these issues. Meanwhile, short videos and live streams are complex multimodal items, and integrating multimodal signals improves recommendation performance. Although Multimodal Large Language Models (MLLMs) show strong multimodal understanding and reasoning, their application to cross-domain recommendation remains underexplored. To this end, we propose Reasoning-Guided Cross-Domain Representation Learning (RGCD-Rep), a reasoning-guided framework for cross-domain recommendation from short videos to live streams. RGCD-Rep introduces MLLM reasoning resource-efficiently and learns transferable item representations guided by behavioral collaboration via two-stage training. First, reasoning-aware distillation lets a frozen teacher MLLM generate structured cross-domain reasoning knowledge and distills it into a lightweight student MLLM. Second, transferability-guided cross-domain representation learning decomposes item representations into transferable and domain residual representations. The resulting representations are computed offline and integrated into downstream retrieval tasks, enabling low-cost industrial deployment. Extensive offline experiments demonstrate RGCD-Rep's superiority. After deployment in Kuaishou's live streaming recommendation system, A/B tests show significant gains across multiple core business metrics, confirming its effectiveness and practicality in real industrial scenarios. RGCD-Rep is fully deployed and serves over 400 million users daily.

cs.IR↗
arXiv2026

Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding

Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental issues: Semantic Bias, where outputs collapse into generic linguistic templates; Signal Neglect, where models rely heavily on LLM priors to hallucinate fluent text even in the absence of meaningful signals; and the "BLEU Trap", where high-frequency stopwords inflate n-gram metrics, masking a lack of true semantic fidelity. To resolve these challenges, we move beyond conventional end-to-end pipelines and propose SemKey, a novel multi-stage framework that enforces signal-grounded generation through four decoupled semantic objectives: sentiment, topic, length, and surprisal. We extract these semantic anchors from EEG embeddings directly, then unify them with an Active Retrieval Decoding mechanism, compelling the LLM to ground its token generation in the neural signals rather than defaulting to linguistic priors. Furthermore, we break the BLEU Trap by establishing a comprehensive evaluation protocol using rigorous retrieval and distribution-based metrics such as Fréchet Distance. Extensive experiments demonstrate that SemKey effectively mitigates hallucinations on noise inputs and achieves SOTA performance on these robust protocols. Code will be released upon acceptance at https://github.com/xmed-lab/SemKey.

cs.CL↗
arXiv2026

WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems

Trajectory world models play a crucial role in robotic dynamics learning, planning, and control. While recent works have explored trajectory world models for diverse robotic systems, they struggle to scale to a large number of distinct system dynamics and overlook domain knowledge of physical structures. To address these limitations, we introduce WestWorld, a knoWledge-Encoded Scalable Trajectory World model for diverse robotic systems. To tackle the scalability challenge, we propose a novel system-aware Mixture-of-Experts (Sys-MoE) that dynamically combines and routes specialized experts for different robotic systems via a learnable system embedding. To further enhance zero-shot generalization, we incorporate domain knowledge of robot physical structures by introducing a structural embedding that aligns trajectory representations with morphological information. After pretraining on 89 complex environments spanning diverse morphologies across both simulation and real-world settings, WestWorld achieves significant improvements over competitive baselines in zero- and few-shot trajectory prediction. Additionally, it shows strong scalability across a wide range of robotic environments and significantly improves performance on downstream model-based control for different robots. Finally, we deploy our model on a real-world Unitree Go1, where it demonstrates stable locomotion performance. The code is available at https://github.com/511205787/WestWorld.

cs.LG↗
arXiv2026

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation

Recent autonomous research systems -- AI-Scientist, PaperOrchestra, AutoSOTA, DeepResearch, InternAgent, ResearchAgent and others -- show LLM agents can ideate, run experiments and write papers, but each fixes a particular control-flow shape (linear pipeline, state machine, single-agent loop, or fixed-recipe skill pack) at the framework level. We argue this rigidity has five roots: (1) workflows are dynamic and discipline-specific (lab work, surveys, simulations, theory all loop differently); (2) ideation is bounded by LLM context and cross-domain ideation needs knowledge a single context cannot hold; (3) summary-only views miss the paper body, yet full-text access is uneven, so the cumulative corpus must do the work; (4) a paper's open-source repository is often the only complete specification of its experimental scheme, but the paper-to-code link is neglected; (5) no tool persists cross-run knowledge retrievably into a finite LLM context. We present PARNESS, an open-source framework built on four design moves. (i) A thin DAG kernel with a four-field Agent contract decouples scheduling from domain semantics, so any discipline's loop is expressible as user-editable YAML. (ii) A full-text PDF-parsing and literature-library subsystem indexes paper bodies, figures and tables as typed objects, with graceful abstract-only fall-back. (iii) A knowledge-graph index over papers, ideas, experiments and code repositories, with scenario-typed retrieval (similar / contradictory / cross-domain / counter-intuitive), surfaces a focused slice into each LLM call. (iv) A small extension surface lets any modern coding agent (Claude Code, Cursor, Copilot, OpenCode) add or replace any module. To our knowledge PARNESS is the first open-source system combining declarative pipelines, full-PDF and code-repository indexing, and cross-run knowledge. Source: https://github.com/gtrhythm/PARNESS

cs.SE↗
arXiv2026

Exploring Data-Free LoRA Transferability for Video Diffusion Models

Video diffusion models leveraging step distillation or causal distillation have achieved remarkable performance. However, adapting existing LoRAs to these variants remains a critical challenge due to weight space mismatches. We observe that direct application leads to style degradation and structural collapse, yet the underlying mechanisms remain poorly understood. To fill this gap, we delve into the weight space and identify that the incompatibility stems from spectral interference within shared functional clusters defined over singular subspaces. Specifically, our analysis reveals that while both paradigms respect spectral rigidity, they establish conflicting routing pathways that clash through constructive overload or destructive cancellation. To address this issue, we propose Cluster-Aware Spectral Arbitration (CASA), a data-free framework that dynamically arbitrates between safeguarding the target's manifold and restoring LoRA alignment based on spectral density. Extensive experiments demonstrate that CASA effectively mitigates artifacts and revives LoRA functionality. Our code is available at https://github.com/Noahwangyuchen/CASA

cs.CV↗
arXiv2026

Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models

This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxonomy of game-playing machines. Central to this paradigm is Nemobot, an interactive agentic engineering environment that enables users to create, customize, and deploy LLM-powered game agents while actively engaging with AI-driven strategies. The LLM-based chatbot, integrated within Nemobot, demonstrates its capabilities across four distinct classes of games. For dictionary-based games, it compresses state-action mappings into efficient, generalized models for rapid adaptability. In rigorously solvable games, it employs mathematical reasoning to compute optimal strategies and generates human-readable explanations for its decisions. For heuristic-based games, it synthesizes strategies by combining insights from classical minimax algorithms (see, e.g., shannon1950chess) with crowd-sourced data. Finally, in learning-based games, it utilizes reinforcement learning with human feedback and self-critique to iteratively refine strategies through trial-and-error and imitation learning. Nemobot amplifies this framework by offering a programmable environment where users can experiment with tool-augmented generation and fine-tuning of strategic game agents. From strategic games to role-playing games, Nemobot demonstrates how AI agents can achieve a form of self-programming by integrating crowdsourced learning and human creativity to iteratively refine their own logic. This represents a step toward the long-term goal of self-programming AI.

cs.AI↗
arXiv2026

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models

In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications. Visual token pruning is a promising strategy for reducing the cost of MLLM inference by removing redundant visual tokens. Existing research usually assumes that all attention heads contribute equally to the visual interpretation. However, our study reveals that different heads may capture distinct visual semantics and inherently play distinct roles in visual processing. In light of this observation, we propose HAWK, a head importance-aware visual token pruning method that perceives the varying importance of attention heads in visual tasks to maximize the retention of crucial tokens. By leveraging head importance weights and text-guided attention to assess visual token significance, HAWK effectively retains task-relevant visual tokens while removing redundant ones. The proposed HAWK is entirely training-free and can be seamlessly applied to various MLLMs. Extensive experiments on multiple mainstream vision-language benchmarks demonstrate that HAWK achieves state-of-the-art accuracy. When applied to Qwen2.5-VL, HAWK retains 96.0% of the original accuracy after pruning 80.2% of the visual tokens. Additionally, it reduces end-to-end latency to 74.4% of the original and further decreases GPU memory usage across the tested models. The code is available at https://github.com/peppery77/HAWK.git.

cs.CV↗