Yihang Lin

Bowen Li, Shaotong Guo, Zhen Wang et al.

Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we present PilotTTS, a lightweight autoregressive TTS system that achieves competitive performance through minimalist architecture and rigorous data engineering. PilotTTS is trained on only 200K hours of data processed entirely with open-source tools. Specifically, our contributions are: (1) a reproducible multi-stage data processing pipeline covering quality assessment, label annotation, and filtering, and (2) a compact model architecture that employs Q-Former-based conditioning to decouple speaker identity from speaking style via cross-sample paired training. Within a unified framework, PilotTTS supports zero-shot voice cloning, emotion synthesis (11 categories), paralinguistic synthesis (4 categories), and Chinese dialect synthesis (14 dialects). On the Seed-TTS Eval benchmark, PilotTTS achieves the lowest WER of 1.50% on test-en, a CER of 0.87% on test-zh, and the highest speaker similarity on both test sets (0.862 and 0.815), outperforming systems trained on significantly larger datasets. We release the complete data pipeline recipe, pretrained weights, and code at https://github.com/AMAPVOICE/PilotTTS.

Yihang Lin, Yunze Gao, Zeyang Lin et al.

With the rapid advancement of large language models, evaluating human-likeness in open-ended conversation has become increasingly important. However, human-likeness is a form of tacit knowledge that humans perceive intuitively, yet the underlying criteria resist explicit formulation. Human judgments vary widely, with strong agreement on some cases and legitimate disagreement on others. Meanwhile, the criteria behind human judgments remain implicit, leaving no clear basis for constructing cases. Further, what counts as human-like is not static, but evolving with model capability and human expectations. Despite progress in evaluation methods such as expert-authored benchmarks, Reward Models, and self-evolving benchmarks, none addresses all three challenges simultaneously. Therefore, we propose GrowLoop, a self-evolving conversation evaluation system that continuously adapts as models advance and scenarios shift. With minimal human seed annotations as the first mover, LLM agents iteratively extract and refine evaluation rubrics through Heuristic Learning. Human-AI agreement is required where annotators converge, while only plausibility is expected where they diverge. Moreover, the Rubric-Case co-evolution mechanism enables continuous evolution, expanded through new seeds when the evaluation target moves. Applied to human-likeness evaluation in open-ended conversation, the generated rubrics not only substantially outperform existing methods in alignment with human judgments, but also uncover issues that annotators overlook. The resulting benchmark effectively discriminates models across capability tiers and reveals where they fall short, while generalizing to new scenarios and adapting as models advance. Our work shifts the benchmarking paradigm from manual updates or difficulty scaling to comprehensive, continuous self-evolution.

Yihang Lin, Pengyuan Zhou, Zhiqian Wu et al.

Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participants' datasets, has recently been found responsible for federated learning's vulnerability in the face of backdoor attacks. Existing defense methods fall short from two perspectives: 1) they consider only very specific and limited attacker models and unable to cope with advanced backdoor attacks, such as distributed backdoor attacks, which break down the global trigger into multiple distributed triggers. 2) they conduct detection based on model granularity thus the performance gets impacted by the model dimension. To address these challenges, we propose Federated Layer Detection (FLD), a novel model filtering approach for effectively defending against backdoor attacks. FLD examines the models based on layer granularity to capture the complete model details and effectively detect potential backdoor models regardless of model dimension. We provide theoretical analysis and proof for the convergence of FLD. Extensive experiments demonstrate that FLD effectively mitigates state-of-the-art backdoor attacks with negligible impact on the accuracy of the primary task.

Haoran Li, XiaoLu Li, Yihang Lin et al.

Video prediction is a complex time-series forecasting task with great potential in many use cases. However, traditional methods prioritize accuracy and overlook slow prediction speeds due to complex model structures, redundant information, and excessive GPU memory consumption. These methods often predict frames sequentially, making acceleration difficult and limiting their applicability in real-time scenarios like danger prediction and warning.Therefore, we propose a transformer-based keypoint prediction neural network (TKN). TKN extracts dynamic content from video frames in an unsupervised manner, reducing redundant feature computation. And, TKN uses an acceleration matrix to reduce the computational cost of attention and employs a parallel computing structure for prediction acceleration. To the best of our knowledge, TKN is the first real-time video prediction solution that achieves a prediction rate of 1,176 fps, significantly reducing computation costs while maintaining other performance. Qualitative and quantitative experiments on multiple datasets have demonstrated the superiority of our method, suggesting that TKN has great application potential.

Chenyu Zhao, Shenglin Zhang, Yihang Lin et al.

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Layer, and a Guidance Gate. The Telemetry Layer preserves fine-grained runtime signals, the Diagnosis Layer fuses cross-signal evidence into grounded diagnoses, and the Guidance Gate produces diagnosis-derived guidance only when it is evidence-grounded, actionable, and within the scope of agent-side behavior. We evaluate PROBE across three settings: repository-level software repair, enterprise workflow recovery, and AIOps service mitigation. On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points. The results reveal a diagnosis-recovery gap: accurate diagnosis is necessary but insufficient unless translated into bounded guidance that a subsequent attempt can execute and verify. Beyond controlled evaluation, a Microsoft IcM prototype shows that PROBE can attach as a non-intrusive side channel to existing service-diagnosis workflows without changing the agent policy, toolset, or execution budget. These results suggest that telemetry-grounded, failure-anchored recovery can improve post-failure recoverability under realistic engineering constraints.

Li Zhou, Lutong Yu, You Lyu et al.

Speech Language Models (SLMs) have made significant progress in spoken language understanding. Yet it remains unclear whether they can fully perceive non lexical vocal cues alongside spoken words, and respond with empathy that aligns with both emotional and contextual factors. Existing benchmarks typically evaluate linguistic, acoustic, reasoning, or dialogue abilities in isolation, overlooking the integration of these skills that is crucial for human-like, emotionally intelligent conversation. We present EchoMind, the first interrelated, multi-level benchmark that simulates the cognitive process of empathetic dialogue through sequential, context-linked tasks: spoken-content understanding, vocal-cue perception, integrated reasoning, and response generation. All tasks share identical and semantically neutral scripts that are free of explicit emotional or contextual cues, and controlled variations in vocal style are used to test the effect of delivery independent of the transcript. EchoMind is grounded in an empathy-oriented framework spanning 3 coarse and 12 fine-grained dimensions, encompassing 39 vocal attributes, and evaluated using both objective and subjective metrics. Testing 12 advanced SLMs reveals that even state-of-the-art models struggle with high-expressive vocal cues, limiting empathetic response quality. Analyses of prompt strength, speech source, and ideal vocal cue recognition reveal persistent weaknesses in instruction-following, resilience to natural speech variability, and effective use of vocal cues for empathy. These results underscore the need for SLMs that integrate linguistic content with diverse vocal cues to achieve truly empathetic conversational ability.