Researcher profile

Rongxiang Weng

Rongxiang Weng contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computation and Language Artificial Intelligence Machine Learning

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

8works

0followers

3topics

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

Efficient Context Scaling with LongCat ZigZag Attention

We introduce LongCat ZigZag Attention (LoZA), which is a sparse attention scheme designed to transform any existing full-attention models into sparse versions with rather limited compute budget. In long-context scenarios, LoZA can achieve significant speed-ups both for prefill-intensive (e.g., retrieval-augmented generation) and decode-intensive (e.g., tool-integrated reasoning) cases. Specifically, by applying LoZA to LongCat-Flash during mid-training, we serve LongCat-Flash-Exp as a long-context foundation model that can swiftly process up to 1 million tokens, enabling efficient long-term reasoning and long-horizon agentic capabilities.

preprint2026arXiv

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization

Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward dimensions often destabilize the construction of scalar advantages. To address these challenges, we propose Reward-Decorrelated Policy Optimization (RDPO), a reward-processing method designed to explicitly target both failure modes. RDPO first utilizes Magnitude-Aware Quantile normalization to stabilize prompt-level advantage allocation across binary, fractional, and continuous rewards. It then applies Mahalanobis whitening within each active reward subspace to mitigate correlation redundancy prior to aggregation. When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations.

preprint2026arXiv

Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens should monotonically improve performance. However, we demonstrate that this assumption sometimes fails to hold in strong-to-weak OPD settings. While later segments of a generated trajectory may still exhibit a non-zero teacher-student advantage, they frequently lack the local contrast that makes dense feedback effective for prioritizing student learning. We term this failure mode local teachability collapse. The resulting principle is straightforward: supervision should concentrate on trajectory regions where the teacher's feedback remains discriminative, rather than uniformly covering the entire response. We operationalize this principle through a trajectory-specific release rule. This rule measures the teacher's margin over the student's top-$K$ candidate set, aggregates this margin across NLTK-tokenized sentence segments, and truncates dense OPD supervision upon detecting a BIC-style downward change point. Experimental results across strong-to-weak distillation tasks using the Qwen3 model family indicate that this release rule consistently outperforms standard full-trajectory OPD across five in-domain benchmarks at various student scales. Furthermore, compared to baseline distillation methods, our approach better preserves model capabilities on out-of-domain task. These results suggest that effective strong-to-weak OPD requires evaluating not only the availability of teacher guidance but also its local utility, ensuring that the generated feedback remains teachable.

preprint2026arXiv

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Enabling Large Language Models (LLMs) to effectively utilize tools in multi-turn interactions is essential for building capable autonomous agents. However, acquiring diverse and realistic multi-turn tool-use data remains a significant challenge. In this work, we propose a novel text-based paradigm. We observe that textual corpora naturally contain rich, multi-step problem-solving experiences, which can serve as an untapped, scalable, and authentic data source for multi-turn tool-use tasks. Based on this insight, we introduce GEM, a data synthesis pipeline that enables the generation and extraction of multi-turn tool-use trajectories from text corpora through a four-stage process: relevance filtering, workflow & tool extraction, trajectory grounding, and complexity refinement. To reduce the computational cost, we further train a specialized Trajectory Synthesizer via supervised fine-tuning. This model distills the complex generation pipeline into an efficient, end-to-end trajectory generator. Experiments demonstrate that our GEM-32B achieve a 16.5% improvement on the BFCL V3 Multi-turn benchmark. Our models partially surpass the performance of models trained on τ - bench (Airline and Retail) in-domain data, highlighting the superior generalization capability derived from our text-based synthesis paradigm. Notably, our Trajectory Synthesizer matches the quality of the full pipeline while significantly reducing inference latency and costs.

preprint2022arXiv

Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation

The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, and thus produce a model capable of generalizing to unseen instances. However, it is commonly observed that the generalization performance of the model is highly influenced by the amount of parallel data used in training. Although data augmentation is widely used to enrich the training data, conventional methods with discrete manipulations fail to generate diverse and faithful training samples. In this paper, we present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT), which augments each training instance with an adjacency semantic region that could cover adequate variants of literal expression under the same meaning. We conduct extensive experiments on both rich-resource and low-resource settings involving various language pairs, including WMT14 English-{German,French}, NIST Chinese-English and multiple low-resource IWSLT translation tasks. The provided empirical evidences show that CsaNMT sets a new level of performance among existing augmentation techniques, improving on the state-of-the-art by a large margin. The core codes are contained in Appendix E.

preprint2020arXiv

AR: Auto-Repair the Synthetic Data for Neural Machine Translation

Compared with only using limited authentic parallel data as training corpus, many studies have proved that incorporating synthetic parallel data, which generated by back translation (BT) or forward translation (FT, or selftraining), into the NMT training process can significantly improve translation quality. However, as a well-known shortcoming, synthetic parallel data is noisy because they are generated by an imperfect NMT system. As a result, the improvements in translation quality bring by the synthetic parallel data are greatly diminished. In this paper, we propose a novel Auto- Repair (AR) framework to improve the quality of synthetic data. Our proposed AR model can learn the transformation from low quality (noisy) input sentence to high quality sentence based on large scale monolingual data with BT and FT techniques. The noise in synthetic parallel data will be sufficiently eliminated by the proposed AR model and then the repaired synthetic parallel data can help the NMT models to achieve larger improvements. Experimental results show that our approach can effective improve the quality of synthetic parallel data and the NMT model with the repaired synthetic data achieves consistent improvements on both WMT14 EN!DE and IWSLT14 DE!EN translation tasks.

preprint2020arXiv

GRET: Global Representation Enhanced Transformer

Transformer, based on the encoder-decoder framework, has achieved state-of-the-art performance on several natural language generation tasks. The encoder maps the words in the input sentence into a sequence of hidden states, which are then fed into the decoder to generate the output sentence. These hidden states usually correspond to the input words and focus on capturing local information. However, the global (sentence level) information is seldom explored, leaving room for the improvement of generation quality. In this paper, we propose a novel global representation enhanced Transformer (GRET) to explicitly model global representation in the Transformer network. Specifically, in the proposed model, an external state is generated for the global representation from the encoder. The global representation is then fused into the decoder during the decoding process to improve generation quality. We conduct experiments in two text generation tasks: machine translation and text summarization. Experimental results on four WMT machine translation tasks and LCSTS text summarization task demonstrate the effectiveness of the proposed approach on natural language generation.

preprint2020arXiv

Multiscale Collaborative Deep Models for Neural Machine Translation

Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train. In this paper, we present a MultiScale Collaborative (MSC) framework to ease the training of NMT models that are substantially deeper than those used previously. We explicitly boost the gradient back-propagation from top to bottom levels by introducing a block-scale collaboration mechanism into deep NMT models. Then, instead of forcing the whole encoder stack directly learns a desired representation, we let each encoder block learns a fine-grained representation and enhance it by encoding spatial dependencies using a context-scale collaboration. We provide empirical evidence showing that the MSC nets are easy to optimize and can obtain improvements of translation quality from considerably increased depth. On IWSLT translation tasks with three translation directions, our extremely deep models (with 72-layer encoders) surpass strong baselines by +2.2~+3.1 BLEU points. In addition, our deep MSC achieves a BLEU score of 30.56 on WMT14 English-German task that significantly outperforms state-of-the-art deep NMT models.

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