Searcharxiv⌕ Search

arXiv subjects

Yi Ren

Publications and source records attributed to Yi Ren.

At least 19 recordsLinked to original sources
arXiv2026

Learning Dynamics of On-Policy Distillation

On-policy distillation (OPD) is emerging as an important paradigm for language-model post-training, combining dense teacher supervision with training on student-generated trajectories. This creates a feedback loop where each update changes the student and thereby the training distribution that generates subsequent updates. Yet, how this feedback shapes learning and generalization remains poorly understood. We conduct a mechanistic analysis of OPD's learning dynamics, distinguishing the two feedback loop stages: conversion of the distillation signal into parameter updates, and broadcast through which these updates change predictions across prefixes and reshape the rollout distribution. This framework helps us understand both limited student responsiveness despite substantial teacher-student disagreement, and degeneration when updates that improve local teacher agreement also increase the probability of unsuccessful continuations, exposing the student to unreliable supervision in subsequent rollouts. Finally, we show that offline distillation can prepare a student for OPD without significantly improving immediate held-out accuracy. While OPD alone may degrade generation, it can yield substantial accuracy gains after sufficient offline preparation. Together, our results connect teacher supervision, student geometry, and the evolving rollout distribution in determining the learning dynamics of OPD and its effects on downstream performance.

cs.LG↗
arXiv2026

Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations

Successfully automating dexterous, long-horizon bimanual manipulation requires frameworks capable of both high-level reasoning and fine-grained execution. Traditional task and motion planning (TAMP), while excellent at symbolic planning, is often brittle in contact-rich operations. Simultaneously, imitation learning (IL), while effective in manipulation tasks with visual feedback, is limited by its low capability in spatial generalization and multi-stage operation. To reconcile their complementary strengths and limitations, we propose DR-LfD (Decomposed and Reorganized Skills Learned from Demonstrations), a framework that integrates visuomotor policies into a TAMP-gated decision-making system. Based on contact relationships, DR-LfD decomposes human demonstrations into atomic skills, which are reproduced as visuomotor policies or object-centric primitives. The initiation, termination, and constraints of the visuomotor policies are carefully modeled and implemented in a TAMP-compatible form, enabling reorganization of skills learned from different sources. DR-LfD transforms the learning problem from one requiring exponential demonstration data over possible skill sequences to one whose demonstration burden scales with the number of distinct skill types, with limited data for each skill. Real-world and simulation benchmarks demonstrate data-efficient skill composition under unseen setups and physical constraints. On two DexMimicGen tasks, DR-LfD with 100 demonstrations outperforms diffusion-based imitation policies with 1000.

cs.RO↗
arXiv2026

HeyGen Voice: Scene-Aware Voice Cloning for Talking Videos

Most voice-cloning systems are built for audio alone: they copy the reference recording's delivery and acoustics, so a voice cloned on a phone sounds like a phone recording whether the speaker is pictured in a studio, on a street, or in a cathedral. Speech for a talking video should sound like the pictured person speaking in the pictured place. We present HeyGen Voice, a scene-aware voice-cloning model that separates who is speaking from how and where: it keeps the speaker's voice from an everyday recording while the target image sets the delivery and acoustics. Prior image-conditioned TTS does half of this job: it either adds scene acoustics without keeping a specific speaker or infers a voice from a face. HeyGen Voice is a multimodal autoregressive transformer conditioned on the image, speaker and scene captions, and the voice recording, trained in five stages that move from multilingual TTS pretraining through simulated and real cross-scene adaptation to reinforcement and preference optimization. Two clone policies trade scene adaptation against fidelity to the original recording, and an audio anchor holds long scripts in one voice and one acoustic environment. Listeners prefer HeyGen Voice over leading commercial systems across a third-party arena, production votes, and talking-video studies: it ranks first (Elo 1201) on the public Artificial Analysis controlled-voice TTS leaderboard (October 2026); in a blind test, users cloning their own voice chose it over ElevenLabs v4 and Cartesia Sonic 3.6 in 62% and 54% of votes; and volunteers rated talking videos of their own digital twin about 10 to 30 points higher (out of 100) when voiced by HeyGen Voice than by leading commercial alternatives. Try HeyGen Voice and hear samples at https://heygen.com/heygen-voice.

cs.SD↗
arXiv2026

DGS-Net: Learning Dexterous Grasps from Single-View Point Clouds via a Multi-Object Scene Dataset

Dexterous grasping in multi-object scene constitutes a fundamental challenge in robotic manipulation. Current mainstream grasping datasets predominantly focus on single-object scenarios and predefined grasp configurations, often neglecting environmental interference and the modeling of dexterous pre-grasp gesture, thereby limiting their generalizability in real-world applications. To address this, we propose DGS-Net, an end-to-end grasp prediction network capable of learning dense grasp configurations from single-view point clouds in multi-object scene. Furthermore, we propose a two-stage grasp data generation strategy that progresses from dense single-object grasp synthesis to dense scene-level grasp generation. Our dataset comprises 307 objects, 240 multi-object scenes, and over 350k validated grasps. By explicitly modeling grasp offsets and pre-grasp configurations, the dataset provides more robust and accurate supervision for dexterous grasp learning. Experimental results show that DGS-Net achieves grasp success rates of 88.63\% in simulation and 78.98\% on a real robotic platform, while exhibiting lower penetration with a mean penetration depth of 0.375 mm and penetration volume of 559.45 mm^3, outperforming existing methods and demonstrating strong effectiveness and generalization capability. Our dataset is available at https://github.com/4taotao8/DGS-Net.

cs.RO↗
arXiv2026

A Wireless World Model for AI-Native 6G Networks

Integrating AI into the physical layer is a cornerstone of 6G networks. However, current data-driven approaches struggle to generalize across dynamic environments because they lack an intrinsic understanding of electromagnetic wave propagation. We introduce the Wireless World Model (WWM), a multi-modal foundation framework predicting the spatiotemporal evolution of wireless channels by internalizing the causal relationship between 3D geometry and signal dynamics. Pre-trained on a massive ray-traced multi-modal dataset, WWM overcomes the data authenticity gap, further validated under real-world measurement data. Using a joint-embedding predictive architecture with a multi-modal mixture-of-experts Transformer, WWM fuses channel state information, 3D point clouds, and user trajectories into a unified representation. Across the five key downstream tasks supported by WWM, it achieves remarkable performance in seen environments, unseen generalization scenarios, and real-world measurements, consistently outperforming SOTA uni-modal foundation models and task-specific models. This paves the way for physics-aware 6G intelligence that adapts to the physical world.

cs.NI↗
arXiv2026

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native models developed to explore this path through agentic post-training. Our system combines a heterogeneous model pool with intelligent routing, recording the predicted capability demand, selected service tier, and subsequent interaction for each user turn. These records are converted into training examples that preserve interleaved reasoning, tool calls, and harness context, and are admitted through structural validation, six-dimensional semantic evaluation, and subscene-level labeling. Routing signals organize supervised fine-tuning into a three-stage curriculum and extend to routing-guided on-policy distillation, where a teacher supervises student-generated responses under the same progression. Capability-guided allocation then converts evaluation feedback into the next training mixture, closing an evaluation-selection-update loop in which what the system learns to do shapes what it learns from next. Across eleven benchmarks covering harness-based agents, tool use, coding, and instruction following, post-training raises the macro-average from 58.94 to 64.87 at 4B and from 65.60 to 69.04 at 9B, substantially narrowing the aggregate gap between the post-trained 4B model and the 9B base model. We further adapt NeoHorse-1-4B into NeoHorse-Jev-4B, a prefill-only model that returns structured decisions and probabilities for agent workflows. NeoHorse-1 provides an initial prototype of this feedback-driven process and a path toward harness-mediated RSI across successive iterations.

cs.CL↗
arXiv2026

Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss

Modern language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a recurring cycle: decide which experience to learn from, understand what that update changes, and remain capable of learning from what comes next. We show that these challenges are governed by the same evolving update--behavior interaction. We derive a token- and layer-wise decomposition of how learning from one token changes another prediction. By separating the softmax force, shared readout geometry, and residual connections, it exposes two interaction channels and yields a forward-computable approximation. Following this interaction through time reveals a unified picture of continual adaptation. Positive interaction identifies useful experience; negative interaction produces either concentrated collision or accumulated erosion; over longer horizons, updates reshape the shared geometry mediating future learning signals, reducing their transmission. These predictions lead to effective data selection, mechanism-specific controls for interference, and a readout-based diagnostic of future learnability whose degradation predicts the benefit of restoring the readout. Across models and training regimes, the same local interaction thus explains both what an update changes now and how learning today changes what can be learned tomorrow. This view connects data attribution, forgetting, and plasticity loss as distinct regimes of the same evolving learning dynamics.

cs.LG↗
arXiv2026

Real-Time Shape Control of Multi-Segment Soft Robotic Arms Using Koopman Operators with Global and Local Observables

Multi-segment soft robotic arms can continuously reconfigure their body shapes for safe interaction, but tip control alone is insufficient for constrained-space tasks. Therefore, shape control is a more important task for multi-segment soft arms than tip control, but remains challenging due to the high dimensionality and nonlinear dynamics of continuum deformation. In existing work, shape control accuracy is defined by the error in the global frame (global shape error). For multi-segment soft arms, using only global shape error as the control objective is insufficient, as segment coupling, gravity-induced loading, and inertial effects become more significant. This difficulty increases with the number of segments. In this paper, we present a Koopman-based model predictive control framework that combines global and local observables, enabling real-time shape control on multi-segment soft robotic arms. The framework is evaluated through numerical and physical experiments. Numerical experiments demonstrate the scalability of the proposed controller by achieving shape control on robots with up to 10 independently actuated segments. The physical experiments demonstrate that the controller is capable of (1) real-time shape control of 3- and 5-segment robotic arms with tip speeds up to 0.6 m/s, (2) robust tracking without retraining, including distal payloads up to 400~g and recovery from a 7~N lateral disturbance, and (3) the potential for future inspection applications through a confined-space demonstration. These results demonstrate that the proposed framework enables dynamic, scalable, and accurate real-time shape control on multi-segment soft robotic arms.

cs.RO↗
arXiv2026

Arm-Aware Guided Dexterous Grasp Generation with Arm-Agnostic Grasp Models

Dexterous grasp generation that considers arm-related constraints is crucial in real-world scenarios involving arm environment collision avoidance, workspace boundary grasps, and consecutive grasping. Existing hand-centric grasp models, which primarily focus on the floating hand's pose, are insufficient for such cases. Conventional arm-aware methods either rely on rejection sampling to discard infeasible samples or require retraining on arm-specific data, leading to low sample efficiency under adverse conditions or limited generalization across different robots and environments. To overcome these limitations, this letter presents an arm-aware dexterous grasp generation framework that leverages pretrained arm-agnostic grasp models while integrating arm and environmental information only at inference time. Specifically, we formulate arm-aware constrained grasp generation as a joint optimization of hand pose and arm configuration, and derive closed-form gradients for arm-related constraints. Assuming the hand pose distribution is represented by a diffusion model, we prove that gradient-based optimization is equivalent to guided diffusion sampling, steering near-feasible samples toward the feasible region. Through comprehensive evaluation involving 10k objects across 6 scenarios, we demonstrate that the proposed framework generates feasible grasps in highly constrained settings with significantly higher probability, highlighting its advantages in real-world applications. Supplementary materials and appendix are available at https://arm-aware-dexgrasp.github.io/.

cs.RO↗
arXiv2026

TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions

Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this fundamental limitation by formalizing the Shot Transition Detection (STD) task. Rather than searching for ambiguous points, STD explicitly detects the continuous temporal segments of transitions. To tackle this, we propose TransVLM, a Vision-Language Model (VLM) framework for STD. Unlike regular VLMs that predominantly rely on spatial semantics and struggle with fine-grained inter-shot dynamics, our method explicitly injects optical flow as a critical motion prior at the input stage. Through a simple yet effective feature-fusion strategy, TransVLM directly processes concatenated color and motion representations, significantly enhancing its temporal awareness without incurring any additional visual token overhead on the language backbone. To overcome the severe class imbalance in public data, we design a scalable data engine to synthesize diverse transition videos for robust training, alongside a comprehensive benchmark for STD. Extensive experiments demonstrate that TransVLM achieves superior overall performance, outperforming traditional heuristic methods, specialized spatiotemporal networks, and top-tier VLMs. For more related research, please visit HeyGen Research (https://www.heygen.com/research) and HeyGen Avatar-V (https://www.heygen.com/research/avatar-v-model). Project page: https://chence17.github.io/TransVLM/

cs.CV↗
arXiv2026

CoorGrasp: Coordinated Contact Control for Adaptive Dexterous Grasping Under Uncertainty

While recent research has focused heavily on dexterous grasp pose generation, less attention has been devoted to the execution of planned grasps. Under shape and position uncertainty, open-loop execution often yields uncoordinated contacts, causing undesired in-hand object motion and even grasp failures. To address this, this paper proposes a tactile-driven model predictive controller for adaptive and delicate execution of diverse dexterous grasps. Our approach emphasizes multi-contact coordination across both approaching and grasping phases, with three key novelties: (i) coordination-aware phase separation, (ii) arm-hand coordination to compensate for position errors, and (iii) adaptive force coordination to increase contact forces in a balanced manner. An analytical model is employed to relate contact forces to robot joint motions for predictive control. Our formulation imposes no restrictions on grasp types or contact configurations and integrates seamlessly with state-of-the-art grasp pose generation methods. We validate the approach through large-scale simulations involving 15k grasps across 478 objects on three robotic hands, and real-world experiments on 8 objects. Results demonstrate that our method achieves higher grasp success rates and reduced undesired object movements.

cs.RO↗
arXiv2026

CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation

Deploying Video Diffusion Models (VDMs) on edge devices is appealing for localized and privacy-preserving generation, but their iterative Transformer-based denoising remains too slow for practical local inference. Cross-Timestep Caching (CTC) has emerged as a promising direction for reducing redundant computation, reusing activations across adjacent denoising steps rather than modifying model weights, while largely preserving generation fidelity. However, on memory-constrained edge GPUs, CTC requires a massive cache footprint that quickly exceeds on-device VRAM and forces the cache into host memory. More fundamentally, cache operators remain tightly interleaved and chain-dependent with native compute operators, so naive near-memory offloading still incurs repeated PCIe exchanges for residual and fusion computations, turning cache reuse into a communication- and serialization-bound execution flow. We therefore propose CODA, an algorithm-hardware co-designed architecture centered on Compute-Cache Operator Disaggregation. CODA separates dense compute paths and memory-bound cache paths across the xPU and a lightweight DIMM-side near-memory engine, reorganizes fragmented cache activity into hardware-friendly coalesced segments, and exploits Classifier-Free Guidance (CFG) branch independence to overlap xPU compute with cache-side execution. Experiments show that CODA achieves up to 1.80x end-to-end speedup and 1.74x higher energy efficiency, while preserving competitive generation quality compared with a state-of-the-art caching algorithm.

cs.AR↗
arXiv2026

A Face-on View of Interstellar Dust in the Galactic Plane

Interstellar dust is a fundamental component of the Milky Way, influencing star formation, galactic evolution, and observations across the electromagnetic spectrum. Using red clump stars selected from near- and mid-infrared photometry, together with stellar catalogs from previous studies, we construct dust density maps of the Galactic plane ({$|Z|<25$}\,pc) covering the full $360^\circ$ in longitude and reaching distances up to $7$\,kpc. By applying a U-Net convolutional neural network to invert the line-of-sight extinction distribution, we obtain dust density maps at resolutions of $10$, $50$, and $100$\,pc, which reveal detailed structures including spiral arms, inter-arm spurs, and giant cavities. The dust distribution in the Galactic plane exhibits a morphology closely resembling that of the so-called Phantom galaxy M74. The derived exponential scale length of the Galactic dust disk is $2.90$\,kpc, slightly larger than that of the stellar thin disk. Our publicly available dust maps provide a new benchmark for extinction correction, studies of Galactic structure, and the investigation of the interplay between star formation and the interstellar medium.

astro-ph.GA↗
arXiv2026

mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health

Medical question-answering benchmarks rarely cover the maternal, neonatal, child, and reproductive-health questions a nurse-midwife asks, and, to our knowledge, no public chunk-level relevance benchmark exists for maternal-health guideline retrieval. We release two benchmarks that fill these gaps. mamabench is a scope-filtered QA set of 25,949 items assembled from seven existing expert-authored sources across multiple-choice, short-answer, and rubric-graded tracks; to help users calibrate the LLM judge that scores the rubric track, we re-scope HealthBench's physician-labelled meta-evaluation to the domain. mamaretrieval pairs 3,185 clinical queries with graded (0-6) relevance labels over a 63,650-chunk maternal-health guideline corpus, using a decomposed rubric that distinguishes a chunk that answers a query from one merely on its topic. Three decisions shape both: assemble and filter expert sources rather than author questions, grade relevance rather than binarise it, and measure and disclose the limits of the labels -- scope-classifier agreement, a frontier-judge check, and a pooling-completeness audit -- rather than treat them as an oracle. A companion paper uses the benchmarks to evaluate a deployed on-device assistant; both are released openly for research.

cs.CL↗
arXiv2026

MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar

Maternal and newborn mortality remain among the highest in sub-Saharan Africa, where midwifery care is often delivered by nurses who lack midwifery training to international standards, and consulting authoritative guidance at the point of care is hard: the guidelines are long and connectivity is intermittent. We present MAM-AI, a medical question-answering assistant for nurse-midwives in Zanzibar that runs entirely on a commodity Android device: a question is embedded (EmbeddingGemma, 300M) and matched against a curated corpus of 87 guideline documents (63,650 passages), then answered with citations by a 4B int4 generator (Gemma 4 E4B), fully offline, with no query leaving the device. We evaluate the exact deployed configuration with a layered methodology -- retriever, generator under oracle context, end-to-end, and latency -- scored by LLM judges validated against physician rubrics. The evaluation relocates the hard problem. On-device retrieval is essentially solved: the 300M embedder ranks third of seven retrievers and rivals cloud systems, so the passages the system needs are usually found. The small generator is what remains in doubt: adding retrieved context does not improve its answers, and at 4B it cannot be both helpful and safe at once -- of two same-size candidates, the more helpful one commits genuine dangerous errors, so we deploy the other, which is about twice as faithful to its sources (as faithful as a frontier model), and recover its helpfulness with a redesigned prompt that cuts deflection from 33% to 3%. Corpus quality is decisive for the same reason: where the corpus holds the right passage the answer is specific and actionable, and where it does not it goes vague. MAM-AI is a thoroughly evaluated, open-source research prototype, not a fielded product; the system, knowledge base, benchmarks, and evaluation harness are released.

cs.CL↗
arXiv2026

HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors

Dexterous grasping across diverse object scales requires contact modes ranging from two-finger pinches to bimanual grasps. Existing dexterous grasp synthesis methods reduce the high-dimensional optimization space with manually designed expected contacts and initialization heuristics, which struggle to balance synthesis success rate and diversity. We present HUGS (Human-prior-guided Unified Dexterous Grasp Synthesis), a human-prior-guided framework for unified dexterous grasp synthesis across modes and scales. Instead of directly retargeting human demonstrations, HUGS learns an object-conditioned human prior that captures human grasp preferences and guides downstream force-closure-aware optimization. The prior is trained on a compact self-collected human grasp dataset with 1.8K grasps over 304 objects, providing broad coverage of object scales and contact modes. During synthesis, HUGS adaptively proposes contact modes and wrist initializations, substantially improving the balance between contact-mode coverage and synthesis success rate over heuristic-based methods. With HUGS, we synthesize 3.2M robotic grasps over 157K scenes, spanning object half-diagonal lengths from 2 cm to 30 cm and modes from two-finger to bimanual grasps. Models trained on the synthesized dataset autonomously select appropriate contact modes in the real world, enabling grasping from screws to large boxes.

cs.RO↗
arXiv2026

Learning Moral Diversity: Modelling Individual Perspectives in Moral Classification of Texts

Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators' labels into a single "ground truth", overlooking the inherent subjectivity of the task. In practice, there are disagreements between annotators caused by personal viewpoint or inherent ambiguities, particularly for short tweets. Here, we extend a pretrained language model with a layer that learns annotator-specific features. Our model improves predictions of individual annotations and yields representations that reveal meaningful insights into annotators' moral perspectives. We show that models trained on aggregated labels may hide variation and give a misleading impression of performance. Overall, we demonstrate that disagreement reflects the inherent subjectivity of the task and that modelling individual perspectives creates benefits for moral classification of texts.

cs.CL↗
arXiv2026

Beyond the Sampled Token: Preserving Candidate Support in RLVR

We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the \emph{candidate distribution} for next-token prediction. We formally show that as probability concentrates on the top-$1$ candidate, the expected number of distinct responses collapses to one regardless of the sampling budget $K$. This theoretical implication is further verified by our empirical tracking of top-$N$ candidate probabilities during training, where the top-$1$ candidate progressively dominates while plausible alternatives are suppressed. These findings suggest a key desideratum for effective exploration: \emph{preserving non-negligible probability mass on the top-$N$ candidates}. To this end, we propose Candidate-aware Support Preservation (CaSP), with two complementary designs. Specifically, CaSP redistributes positive gradients among top-$N$ candidates for correct responses, and applies a stronger penalty to the top-$1$ candidate for incorrect responses. Unlike many exploration-oriented methods that improve pass@$K$ at the cost of pass@1, CaSP improves pass@$K$ across the full $K$ spectrum. These gains generalize to 6 math, 2 logical-reasoning, and 2 coding benchmarks, and scales to 32B-parameter models and sampling budgets up to $K=1024$, positioning it as a principled, candidate-level approach for RLVR exploration.

cs.AI↗