Searcharxiv⌕ Search

arXiv subjects

Chenghao Zhang

Publications and source records attributed to Chenghao Zhang.

At least 19 recordsLinked to original sources
arXiv2026

MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning

When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially reference retrieved evidence can mislead clinicians into unsafe treatment decisions. Medical reasoning agents must therefore produce not only correct answers but also faithful justifications that clinicians can verify against cited evidence. We identify a systematic failure mode in RL-trained retrieval agents: outcome-only rewards improve accuracy while degrading faithfulness, a phenomenon we term confident hallucination. The agent learns to answer from parametric memory and backfill plausible but unsupported justifications; citation fabrication rates rise from 16.5% to 31.8% even as accuracy improves by 5 points over the supervised baseline. We address this with a faithfulness-gated reward design: accuracy credit is conditioned on evidence grounding via a hard gate, complemented by retrieval validity and conciseness signals that close exploitation paths unique to agentic retrieval. The resulting system, MedAgent-R1, reduces citation fabrication from 31.8% to 4.7% and raises evidence completeness from 58.7 to 82.6 while maintaining 75.1% accuracy, with 13.2-point gains on HealthBench Safety. Under the same agentic retrieval setup, MedAgent-R1 outscores GPT-4o on faithfulness-specific dimensions (Factual Support 4.55 vs. 4.25; Overclaiming 4.40 vs. 4.15) while remaining below GPT-4o in overall accuracy, suggesting that explicit faithfulness training yields evidence-grounding gains not achieved by scaling alone.

cs.AI↗
arXiv2026

SWIM: Step-Wise Integrated Measure for Session-supervised List Evaluation in Generative Re-ranking

Modern industrial recommender systems have increasingly adopted the Generator-Evaluator (G-E) framework for the re-ranking stage. Within this paradigm, the generator produces candidate item lists from a pool filtered by upstream retrieval and ranking modules, while the evaluator scores these lists and selects the highest-scoring one for final exposure per request. However, on sequential platforms (e.g., short-video apps), users consume items continuously, ignoring artificial list boundaries. Conventional evaluators score lists by aggregating point-wise values, implicitly assuming exposure independence. This fails to capture critical session-level dynamics, such as contextual dependencies, user continuation, and diminishing marginal utility from repetitive content. To bridge this gap, we propose SWIM (Step-Wise Integrated Measure), a list-level evaluator that models user behaviors as a finite-horizon prefix session-level survival process. SWIM estimates the prefix-conditioned contribution of the current list to the session-level objective by factorizing it into a recursive survival distribution and reached-position conditional rewards. Leveraging a causally-masked Transformer, SWIM efficiently estimates continuation probabilities and utilities in parallel, satisfying strict industrial latency constraints. Extensive experiments demonstrate that SWIM significantly outperforms baselines in listwise reranking tasks, yielding substantial improvements in overall recommendation engagement.

cs.IR↗
arXiv2026

From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning

Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDDL annotations and may exploit solver success in semantically unfaithful ways. We study how to learn faithful natural-language-to-PDDL formalization using only solver feedback, without human-written demonstrations. We propose a solvergrounded multi-role reinforcement learning framework where a single language model acts as an Actor, Judge, and Editor for generation, verification, and repair. The Actor proposes PDDL specifications, the Judge provides a solver-calibrated quality signal, and the Editor performs bounded diagnostic-conditioned refinement. On PlanBench, our method improves average success from 35.5% for LLM+P to 70.8%, achieves 66.3% faithful success, and reduces semantic drift to 6.4%. These results show that organizing solver feedback into generation, verification, and repair roles enables more scalable and faithful annotation-free symbolic planning

cs.AI↗
arXiv2026

Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning

Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding broken links, inconsistent states, or infeasible tasks. We address the gap between scalable environment generation and trustworthy agent learning by constructing synthetic web environments that are executable, auditable, and grounded in backend state. Our framework represents each generated website as a structured scaffold of pages, navigation links, database records, state-change markers, and task constraints, then verifies and repairs structural, semantic, consistency, and feasibility defects before policy training. During interaction, ordinary UI transitions are executed deterministically, while persistent backend updates are invoked only through validated state-change markers, enabling dense rewards compiled from verified task-progress predicates. Across 500 synthetic environments spanning six domains, our method reduces task-blocking defects and improves feasible-task rate from 48.6% to 94.8%, while producing stronger PPO policies and improving transfer to WebArena, WebShop, and MiniWoB++ without LLM calls at evaluation time. These results show that verified synthetic environments can serve as a scalable and reliable training substrate for compact web agents, shifting synthetic webagent learning from surface-level plausibility toward executable, state-grounded supervision.

cs.AI↗
arXiv2026

A Machine-Learning Framework for Efficient Ring-Polymer Instanton Rate Calculations

We develop an efficient machine-learning framework for ring-polymer instanton rate calculations that combines Gaussian process regression (GPR)-enhanced line integral string optimization with scalable surrogate modeling of the fluctuation prefactor. By exploiting uncertainty estimates from the surrogate modeling, we show that the number of force evaluations required to converge an instanton path becomes effectively independent of the number of beads used to discretize the pathway. To improve the efficiency of GPR model training, we introduce a strategy combining a physics-informed kernel prior, Hessian-free hyperparameter optimization, and GPU-accelerated Blackbox Matrix-Matrix Multiplication (BBMM), reducing model-training costs by more than an order of magnitude. For rate calculations, we develop adaptive regression, selective Hessian training, and cubic-spline interpolation strategies that substantially reduce the number of explicit Hessian evaluations while maintaining accurate tunneling rates. We apply and compare both cubic spline interpolation and GPR methods to approximate the instanton rate for representative proton transfer systems such as malonaldehyde, Z-3-aminopropenal, and 7,9-dinitro-10-hydroxybenzo[h]quinoline (dinitro-HBQ). Both approaches perform well for the smaller systems, whereas the dinitro-HBQ results expose limitations of the GPR model and demonstrate the greater robustness of the cubic spline interpolation method. These developments provide a practical workflow for reducing the computational cost of instanton rate calculations in complex molecular systems.

physics.chem-ph↗
arXiv2026

mmRadarTwin: A Measurement-Calibrated Signal-Level Digital Twin Platform for Indoor mmWave Radar

Indoor mmWave radar perception is difficult to reproduce because measured range-angle responses depend on scene geometry, material response, multipath, hardware conventions, and signal processing. Existing ray-tracing and digital-twin tools often expose rendering, channel, or path-level quantities, while radar sensing requires complex signal products that can be processed and compared in the same domain as real FMCW measurements. We present mmRadarTwin, a signal-level and path-attributed digital-twin platform for indoor mmWave radar. mmRadarTwin links a real radar measurement branch with an Unreal Engine scene-simulation branch through a shared receive-channel and range-angle processing interface. The simulator writes complex multi-channel receive grids and exports per-path contribution records that identify the actor, material tag, propagation event, and output-bin support of each simulated return. We evaluate mmRadarTwin in an office deployment using a commodity monostatic mmWave radar and mobile scene-capture hardware. Across 154 measured poses spanning 22 radar locations, the current physics-only path-basis simulator recalls 70.8% of measurement-active geometry-supported response regions in the central usable field of view while exposing residuals caused by weak or missing path support, shifted responses, unsupported anchors, and missing physical mechanisms. Rather than claiming complete radar-map reconstruction or cross-room generalization, mmRadarTwin establishes a practical systems workflow for constructing, comparing, and diagnosing indoor radar digital twins.

cs.CV↗
arXiv2026

DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval

Reranking is a combinatorial decision problem that aims to select and order a high-utility slate from a request-specific candidate set. A major line of generative rerankers adopts autoregressive (AR) models, which construct the slate one position at a time to capture inter-position dependencies. However, under practical greedy or bounded-width decoding, prefix-based search may prematurely prune globally promising permutations and incurs inherently sequential latency, restricting the effective search space under a fixed serving budget. Non-autoregressive (NAR) alternatives alleviate this efficiency bottleneck through position-parallel prediction, but naive position-wise factorization treats different positions too independently, leading to insufficient cross-position coordination and potentially duplicate or conflicting item selections. To retain parallel efficiency while introducing global structural coordination, we propose Dynamic Index-based RECommendation with Transport-Optimized Retrieval (DIRECTOR), a transport-guided parallel reranking framework. DIRECTOR maps candidate items into a continuous latent space and generates request-conditioned dynamic retrieval indices for all target positions in parallel. During training, it uses entropy-regularized OT to provide conflict-aware supervision; at inference, it directly performs global hard matching on similarity matrix, producing duplicate-free slates without iterative transport. To further align the generator with an opaque list-wise evaluator that returns only a scalar utility, we introduce a prefix-anchored credit assignment mechanism that converts the global reward into position-specific training signals. Extensive offline and online experiments demonstrate that DIRECTOR consistently outperforms strong reranking baselines, achieving significant improvement in large-scale industrial recommendation scenarios.

cs.IR↗
arXiv2026

PSG: Pair-Space Generation for Efficient Generative Reranking

Modern recommender systems adopt Generator-Evaluator (G-E) for list-wise reranking: a generator produces sequences from candidates and an evaluator scores them at sequence-level to filter out the optimal one for exposure. Auto-Regressive(AR), working as the backbone for generative recommendation, suffers two limitations. First, its complexity grows linearly with list length, forcing the system to generate fewer lists under rigorous latency constraints and thus limiting exploration. Second, teacher-forcing creates a train-test mismatch; cumulative errors worsen with length and degrade quality. To address these problems, we propose Pair-Space Generation (PSG), a reformulation that elevates the generation atom from individual items to ordered item pairs. Given $n$ candidate items, PSG operates over pair vocabulary of size $n(n-1)$ per request, generates only $L/2$ tokens. Pair token representations are produced on-the-fly by a pretrained pair-token representation module optimized over large scale exposure logs, eliminating the data sparsity that would otherwise plague a quadratic sized vocabulary. We establish three theoretical guarantees: (i) PSG is bijective with item-space generation and induces an equivalent family of sequence distributions, thus incurring no loss of expressiveness; (ii) generation in pair-token space achieves approximately a $2\times$ to $4\times$ speedup theoretically under moderate settings and $1.83\times$ in the real industrial environmental settings; and (iii) under outcome-only rewards, the worst-case suboptimality of PSG is bounded by $O((L/2)^2 \barε)$, representing a nearly $4\times$ improvement over item-space generation. Beyond benchmark-based validation, PSG has also been deployed on Kuaishou, delivering a 0.178\% lift in per-user stay time on the platform, which serves over 400 million daily active users.

cs.IR↗
arXiv2026

FlashEvaluator: Expanding Search Space with Parallel Sequence-Level Evaluation

The Generator-Evaluator (G-E) framework generates K candidate sequences and uses an evaluator to select the highest-scoring one, which is widely used in recommender systems (RecSys) and natural language processing (NLP). Existing evaluators commonly score candidates independently. Although such evaluations can be batched, independent scoring neither models interactions among candidates nor eliminates repeated computation of request-level context and recurring candidate elements, causing the total evaluation work to grow approximately linearly with K. To handle with, we propose FlashEvaluator, a joint evaluator that scores all candidate sequences in a single forward pass. FlashEvaluator factorizes evaluation into shared request-level encoding, reusable candidate-side computation, sequence assembly by indexing, and cross-sequence interaction for setwise comparison. We call this request-local reuse scheme QKV-Cache: inspired by autoregressive KV caching, it reuses context-side key/value representations across candidate sequences and, when candidate elements recur, reuses their request-conditioned representations on the query side. In repeated-item settings, the dominant item-encoding cost therefore depends on the number of distinct items rather than their total occurrences across sequences, reducing the marginal cost of evaluating additional candidates. We provide a computational analysis and evaluate FlashEvaluator on recommendation and text summarization. The results show lower latency and higher throughput with competitive recommendation and summarization quality. In an online deployment at Kuaishou with K=50, FlashEvaluator reduces inference latency by 44% and increases QPS by 114% relative to the production baseline, while yielding statistically significant gains in retention, engagement, and ecosystem metrics.

cs.IR↗
arXiv2026

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

cs.CL↗
arXiv2026

Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation

Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose Ptah, a multi-agent harness for interleaved report generation. Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages, where specialized agents construct visual-aware plans, collect claim-grounded evidence, maintain source-aligned images in a Visual Working Memory, and compose reports through declarative multimodal tool use. A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow. We further introduce PtahEval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that Ptah produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines. Our code is released at https://github.com/SnowNation101/Ptah

cs.CL↗
arXiv2026

IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving

End-to-end autonomous driving has emerged as a compelling paradigm for learning planning directly from sensor observations, while recent world-model-based approaches further enrich this paradigm by enabling explicit reasoning about how the scene may evolve in the future. Yet future prediction alone does not guarantee better planning unless the predicted evolution can be converted into planning-relevant trajectory updates. Many current methods still forecast future scene states without explicitly decoding the motion implications hidden in state transitions. As a result, future reasoning often remains descriptively useful but only weakly coupled to executable motion generation. To address this limitation, we propose \mathbf{IDOL}, an inverse-dynamics-guided future prediction framework for world-model-based end-to-end planning in latent BEV space, where inverse dynamics serves as the key bridge between future prediction and trajectory optimization. IDOL first predicts multiple future latent scene states with a BEV world model, then applies an inverse dynamics model to adjacent latent futures to decode transition-aware trajectory features and recover planning-relevant motion deltas that explain how the latent world evolves over time. These inverse-dynamics-derived signals are used to optimize the planned trajectory, turning future forecasting from passive scene anticipation into actionable planning guidance. A lightweight closed-loop refinement module further improves long-horizon consistency by reusing the optimized trajectory for another round of future-aware reasoning. By introducing inverse dynamics into latent future reasoning, IDOL tightens the coupling between world modeling and planning. Extensive experiments on the NAVSIM v1 and NAVSIM v2 benchmarks show that IDOL achieves state-of-the-art performance among comparable methods.

cs.RO↗
arXiv2026

ATIR: Towards Audio-Text Interleaved Contextual Retrieval

Audio carries richer information than text, including emotion, speaker traits, and environmental context, while also enabling lower-latency processing compared to speech-to-text pipelines. However, recent multimodal information retrieval research has predominantly focused on images, largely overlooking audio, especially in the setting of interleaved audio-text contextual retrieval. In this work, we introduce the Audio-Text Interleaved contextual Retrieval (ATIR) task, where queries can alternate between audio and text modalities. We construct an ATIR benchmark by integrating several Automatic Speech Recognition (ASR), QA, and retrieval datasets, ultimately unifying four types of contextual retrieval tasks. This benchmark substantially addresses the limitations of existing audio retrieval datasets in semantic retrieval. To study this task, we evaluate several off-the-shelf retrievers and train our ATIR model based on a Multimodal Large Language Model (MLLM). We further introduce a novel token compression mechanism that is orthogonal to existing compression methods, thereby alleviating the issue of excessive audio tokens in MLLM-based ATIR models. Experimental results demonstrate that our ATIR model achieves substantial improvements over strong baselines.

cs.SD↗
arXiv2026

FOCAL-Attention for Heterogeneous Multi-Label Prediction

Heterogeneous graphs have attracted increasing attention for modeling multi-typed entities and relations in complex real-world systems. Multi-label node classification on heterogeneous graphs is challenging due to structural heterogeneity and the need to learn shared representations across multiple labels. Existing methods typically adopt either flexible attention mechanisms or meta-path constrained anchoring, but in heterogeneous multi-label prediction they often suffer from semantic dilution or coverage constraint. Both issues are further amplified under multi-label supervision. We present a theoretical analysis showing that as heterogeneous neighborhoods expand, the attention mass allocated to task-critical (primary) neighborhoods diminishes, and that meta-path constrained aggregation exhibits a dilemma: too few meta-paths intensify coverage constraint, while too many re-introduce dilution. To resolve this coverage-anchoring conflict, we propose FOCAL: Fusion Of Coverage and Anchoring Learning, with two components: coverage-oriented attention (COA) for flexible, unconstrained heterogeneous context aggregation, and anchoring-oriented attention (AOA) that restricts aggregation to meta-path-induced primary semantics. Our theoretical analysis and experimental results further indicates that FOCAL has a better performance than other state-of-the-art methods.

cs.LG↗
arXiv2026

Cycle Inverse-Consistent TransMorph: A Balanced Deep Learning Framework for Brain MRI Registration

Deformable image registration plays a fundamental role in medical image analysis by enabling spatial alignment of anatomical structures across subjects. While recent deep learning-based approaches have significantly improved computational efficiency, many existing methods remain limited in capturing long-range anatomical correspondence and maintaining deformation consistency. In this work, we present a cycle inverse-consistent transformer-based framework for deformable brain MRI registration. The model integrates a Swin-UNet architecture with bidirectional consistency constraints, enabling the joint estimation of forward and backward deformation fields. This design allows the framework to capture both local anatomical details and global spatial relationships while improving deformation stability. We conduct a comprehensive evaluation of the proposed framework on a large multi-center dataset consisting of 2851 T1-weighted brain MRI scans aggregated from 13 public datasets. Experimental results demonstrate that the proposed framework achieves strong and balanced performance across multiple quantitative evaluation metrics while maintaining stable and physically plausible deformation fields. Detailed quantitative comparisons with baseline methods, including ANTs, ICNet, and VoxelMorph, are provided in the appendix. Experimental results demonstrate that CICTM achieves consistently strong performance across multiple evaluation criteria while maintaining stable and physically plausible deformation fields. These properties make the proposed framework suitable for large-scale neuroimaging datasets where both accuracy and deformation stability are critical.

eess.IV↗
arXiv2026

SOLAR: SVD-Optimized Lifelong Attention for Recommendation

Attention mechanism remains the defining operator in Transformers since it provides expressive global credit assignment, yet its $O(N^2 d)$ time and memory cost in sequence length $N$ makes long-context modeling expensive and often forces truncation or other heuristics. Linear attention reduces complexity to $O(N d^2)$ by reordering computation through kernel feature maps, but this reformulation drops the softmax mechanism and shifts the attention score distribution. In recommender systems, low-rank structure in matrices is not a rare case, but rather the default inductive bias in its representation learning, particularly explicit in the user behavior sequence modeling. Leveraging this structure, we introduce SVD-Attention, which is theoretically lossless on low-rank matrices and preserves softmax while reducing attention complexity from $O(N^2 d)$ to $O(Ndr)$. With SVD-Attention, we propose SOLAR, SVD-Optimized Lifelong Attention for Recommendation, a sequence modeling framework that supports behavior sequences of ten-thousand scale and candidate sets of several thousand items in cascading process without any filtering. In Kuaishou's online recommendation scenario, SOLAR delivers a 0.68\% Video Views gain together with additional business metrics improvements.

cs.IR↗
arXiv2025

NVIDIA Nemotron 3: Efficient and Open Intelligence

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to 1M tokens. Super and Ultra models are trained with NVFP4 and incorporate LatentMoE, a novel approach that improves model quality. The two larger models also include MTP layers for faster text generation. All Nemotron 3 models are post-trained using multi-environment reinforcement learning enabling reasoning, multi-step tool use, and support granular reasoning budget control. Nano, the smallest model, outperforms comparable models in accuracy while remaining extremely cost-efficient for inference. Super is optimized for collaborative agents and high-volume workloads such as IT ticket automation. Ultra, the largest model, provides state-of-the-art accuracy and reasoning performance. Nano is released together with its technical report and this white paper, while Super and Ultra will follow in the coming months. We will openly release the model weights, pre- and post-training software, recipes, and all data for which we hold redistribution rights.

cs.CL↗
arXiv2025

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on diverse environments. Nemotron 3 Nano achieves better accuracy than our previous generation Nemotron 2 Nano while activating less than half of the parameters per forward pass. It achieves up to 3.3x higher inference throughput than similarly-sized open models like GPT-OSS-20B and Qwen3-30B-A3B-Thinking-2507, while also being more accurate on popular benchmarks. Nemotron 3 Nano demonstrates enhanced agentic, reasoning, and chat abilities and supports context lengths up to 1M tokens. We release both our pretrained Nemotron 3 Nano 30B-A3B Base and post-trained Nemotron 3 Nano 30B-A3B checkpoints on Hugging Face.

cs.CL↗