Zero-Shot
-
MuseTimbre: Zero-Shot Timbre Transfer by Controlling a Frozen Music Generator
2026-09-24 20:56:50Yuan-Chiao Cheng, Zhiyao DuanAbstract
Instrument timbre transfer re-voices a performance using the timbre of another instrument. Extracting the target timbre from an audio reference capture more nuances than inferring it from a text prompt. Systems that read timbre from such a clip train a dedicated model for the task, which captures the timbre cleanly but stays a narrow, single-purpose system. More versatile approaches add control to a pretrained music generator, yet a reference clip entangles timbre with genre and melody, so these systems fall back on text to name the timbre. We present MuseTimbre, the first system, to our best knowledge, that transfers timbre from an audio reference to a polyphonic source through conditioning a pretrained music generator. This system employs a multi-pitch estimator to extract pitch information from the source and finetune a CLAP encoder to extract timbre information from the reference audio. Experiments show that across four datasets of real polyphonic recordings, MuseTimbre achieves pitch alignment on par with the baselines while matching the reference timbre far more closely. Results also show that the finetuned CLAP-based timbre extractor is robust to pitch variations, making it useful in timbre similarity measures.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30548
PDF
-
GraspTwin: Zero-Shot Task-Oriented Grasp Optimization via a Digital Twin
2026-09-24 20:50:26Daniel J. Evans, Yinlong Dai, Simon Stepputtis, Dylan P. LoseyAbstract
As robots transition from structured factory settings into homes, they are required to interact with an ever-increasing variety of objects. Many tasks require grasping, and often it is not sufficient to just pick up the target object. Consider a task like "pouring coffee" --- to facilitate the subsequent pouring, the robot should grasp the mug by its handle. Existing learning-based approaches for grasping either find robust and collision-free grasps that are largely agnostic to the task (e.g., picking up the mug by its rim), or leverage foundation models to propose task-appropriate grasp locations that lack fine-grained physical grounding (e.g., reaching for and missing the handle). In this work, we bridge these approaches with a real-to-sim-to-real framework. Based on a single RGB-D observation, we construct a digital twin of the environment, query a large foundation model to propose grasps that align with the object's affordances and task description, and then optimize the proposals to ensure robustness and plausibility before executing the result on the real robot. Our key insight is that the grasp proposals of the foundation model should be regarded as semantic priors that serve as seeds for local, gradient-free optimization. We leverage Bayesian optimization with Thompson sampling to draw batches of nearby poses, which are subsequently evaluated in parallel under domain-randomized physics rollouts. The resulting grasp is both task-oriented and physically feasible for execution by the robot arm. Our full zero-shot real-world transfer only takes a few minutes and improves task-oriented grasping success by up to 33% as compared to other state-of-the-art pipelines. Our code is available here: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.30543
PDF
-
CSCWD: Cross-Scale Channel-wise Knowledge Distillation for Lightweight Tiny Object Detection on Edge Devices
2026-09-24 18:02:25Amir Zamani, Zeinab Ghasemi-NaraghiAbstract
Real-time tiny object detection in aerial imagery is constrained by the weak spatial evidence of very small objects and the loss of high-resolution detail in lightweight detectors. This study presents Cross-Scale Channel-wise Knowledge Distillation (CSCWD), a training-time framework that transfers high-resolution spatial representations from a YOLO11m-P2 teacher to a compact YOLO11n student without altering the student's inference architecture. Unlike conventional same-scale feature distillation, CSCWD transfers supervision from teacher P2 to student P3 after feature alignment while retaining same-scale distillation at deeper pyramid levels. Under the unified seven-sequence Drone-vs-Bird validation protocol, YOLO11n-CSCWD achieves 50.17% mean average precision at an intersection-over-union threshold of 0.5 (mAP@0.5) and 59.73% recall, improving the matched CA-YOLO11n baseline by 2.92 percentage points in mAP@0.5 and 3.55 points in recall. Cross-scale alignment further increases mAP@0.5 by 2.09 points over the corresponding same-scale channel-wise distillation configuration. In zero-shot evaluation on DUT-Anti-UAV, mAP@0.5 increases from 48.29% to 50.06% without target-domain fine-tuning. This domain was included because its challenging small targets make low-latency, computationally efficient detection particularly relevant. On Raspberry Pi 5 using NCNN-FP16 at 640x640 resolution, the 2.58-million-parameter student achieves 50.32% mAP@0.5 at 82.32 ms mean wall-clock latency, or 12.15 frames per second, while retaining essentially the same runtime and memory requirements as the matched baseline. The results support cross-scale distillation for improving tiny-target detection without increasing inference-time model complexity.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30395
PDF
-
AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
2026-09-24 17:59:41Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi, Jing Huo, Yang GaoAbstract
Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions. We introduce AD-WM, an action-discriminative joint-embedding world model for counterfactual MPC. AD-WM combines residual latent dynamics with predictor-level action-recovery regularization, using inverse dynamics and a normalized recovery objective motivated by conditional mutual information. Both objectives encourage planning transitions to preserve action information; their auxiliary heads are discarded at test time, leaving MPC unchanged. On OGBench-Cube, AD-WM improves hard-start success from 3.7% to 52.0% over a matched LeWM baseline and improves mean success over the reproduced baseline in four of five simulation environments. Planning diagnostics show that factual prediction error and whole-bank action ranking do not follow the closed-loop success ordering, whereas CEM-aligned elite regret tracks success more closely. With a frozen V-JEPA 2 encoder and matched DROID post-training, AD-WM also improves zero-shot transfer to our Franka setup, increasing basic pick-and-place success from 42.2% to 71.1% without lab-specific adaptation. These results suggest that world models for planning should preserve action-dependent differences needed for counterfactual selection, rather than optimize factual prediction accuracy alone. More videos and code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30264
PDF
-
Self-Play Pretraining with Zero Data
2026-09-24 16:23:01Aditya Cowsik, Kfir Dolev, Michael Y. Li, G. Bruno De Luca, Nourya Cohen, Noah D. Goodman, Yoav LevineAbstract
Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's behalf. A more general approach to pretraining would let the model learn to generate the data most useful for its own improvement. This would provide an effectively unbounded source of training data, limited by compute rather than human knowledge. We introduce Self-Play Pretraining with Zero Data, an initial proof-of-concept towards realizing this vision. Our procedure casts synthetic data generation as a search over the space of all computable structure, taking inspiration from Solomonoff induction. Starting from random initialization, two models learn in tandem: a generator proposes programs interpreted by a universal Turing machine, generating byte sequences, while a learner autoregressively predicts these byte sequences. The learner is trained with standard cross-entropy, while the generator is trained with reinforcement learning to produce sequences at the frontier of the learner's capabilities, yielding an adaptive curriculum. A universal Turing machine gives us a search space over all computable data-generating processes, imposing little domain-specific structure, and self-play searches over this space for useful training data. We test whether zero-shot performance on natural data improves predictably with self-play compute; this is a clean test of transfer since neither generator nor learner is trained on natural data. Across several natural datasets, zero-shot loss exhibits predictable scaling in compute. The models also exhibit in-context learning, and discover recognizable mathematical sequences during training.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30063
PDF
-
Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models
2026-09-24 16:11:21Ehsan Barkhordar, Surendrabikram ThapaAbstract
If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot on current commercial models. Five LLMs generate solutions to MBPP, HumanEval, and DS-1000, seven more to MBPP, and models act as evaluators in four tasks: picking their own solution from a pair, judging whether a single solution is their own, identifying which of two solutions a named model wrote, and judging quality blind. In the single-solution task, balanced accuracy is 49-58% for all 15 model-benchmark combinations, while raw accuracy (38-67%) mostly reflects how readily a model claims authorship. In the pairwise task, accuracy across 14 evaluator-opponent combinations correlates at r=0.93 with how often the evaluator's solution is longer. Attribution to a named model succeeds on some pairs and is consistently inverted on others. A rule-based normalization that strips docstrings, comments, type hints, and local names preserves Pass@1 and leaves ten of twelve re-tested results at chance; the other two follow a length difference it leaves, although a trained classifier still separates most normalized pairs. Claude Haiku's self-preference also disappears. We recommend reporting balanced accuracy, heuristic baselines, and label consistency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30048
PDF
-
VietPrism: A large-scale Vietnamese speech and deepfake corpus with diverse dialects and code-switching
2026-09-24 15:48:23Minh Hoang, Thai LeAbstract
Vietnamese speech research is constrained by resources that isolate automatic speech recognition from speaker, dialect, code-switching, and deepfake analysis. We introduce VietPrism, an open, multi-domain corpus that brings these dimensions together at scale: 993.4 hours and 403,941 bona fide utterances from 1,262 verified speakers across 8,388 real-world videos. To our knowledge, it is the first large-scale Vietnamese corpus to jointly provide transcripts, consistent speaker identities, five dialect groups, and naturally occurring Vietnamese--English code-switching, which constitutes nearly half of the corpus by duration. We further create over 3.1K hours of spoof speech with four open-source and commercial synthesis systems. Every spoof is conditioned on a verified speaker reference and paired with a transcript- and speaker-matched bona fide utterance, enabling unique controlled evaluation with reduced lexical and identity confounds. Zero-shot evaluation of five pretrained multilingual detectors reveals striking brittleness: EER greatly varies across detector--generator pairings, while recent multilingual detector DFA-1B degrades from 16.3% to 33.6% as speaker similarity increases. Dialect-stratified results expose further model-dependent disparities. By unifying natural linguistic diversity with controlled spoof generation, VietPrism provides a challenging foundation for Vietnamese speech modeling and trustworthy audio-deepfake detection.
Abstract (translated)
URL
https://arxiv.org/abs/2609.30005
PDF
-
Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
2026-09-24 15:05:22Jiaqi Deng, Zonghan Wu, Zhan Heng, Xiaoshui Huang, Huan Huo, Guandong XuAbstract
Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on language priors, often generating answers without adequately using task-relevant visual evidence. Existing approaches primarily improve reasoning through reasoning-oriented supervision or inference-time strategies. In this work, we study a complementary question: can multimodal reasoning be improved by strengthening implicit visual grounding without directly supervising the reasoning process? Motivated by the functional specialization of attention heads, we investigate whether reasoning can be improved by guiding only the heads most responsive to visual evidence grounding. We propose Selective Probability Mass Concentration (sPMC), a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention. sPMC treats normalized attention over visual tokens as a spatial probability distribution and encourages the probability mass to be assigned to semantically relevant regions using segmentation-derived spatial priors. Adaptive Head Selection restricts this guidance to visually responsive heads while leaving the remaining heads unconstrained to preserve their complementary functions. Across 6 multimodal benchmark suites, sPMC achieves an average zero-shot improvement of 3% and gains of up to 11.3% across multiple MLLMs while regularizing only 3%-15% of their attention heads. These results demonstrate that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29940
PDF
-
EditVoice: Variable-Length Non-Autoregressive Zero-Shot TTS and Speech Editing with Edit Flows
2026-09-24 14:36:30Hongyao Deng, Wenhao Guan, Xuetao Lin, Peijie Chen, Weijie Wu, Lin Li, Qingyang HongAbstract
Recent non-autoregressive (NAR) zero-shot text-to-speech (TTS) models generate in parallel but typically require the target sequence length to be specified before generation. We introduce EditVoice, to our knowledge the first variable-length NAR zero-shot TTS model, which uses Edit Flows to jointly update speech content and sequence length through insertions, deletions, and substitutions. EditVoice adopts speech-infilling training, which unifies zero-shot TTS and text-based speech editing and allows both prefix and suffix speech prompt placements at inference. We introduce Complementary Prompt Sampling (CPS) to leverage the complementary Edit Flow predictions induced by the two prompt placements. We further find that EditVoice can edit source and model-generated speech beyond its training sources. We use this generalization for end-to-end editing and training-free post-generation refinement. With the Edit Flow model trained on 10K h of GigaSpeech, EditVoice demonstrates competitive zero-shot TTS performance on Seed-TTS Eval EN and LibriSpeech-PC and speech editing performance on RealEdit.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29889
PDF
-
GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments
2026-09-24 14:21:26Guangzhao Dai, Qianru Sun, Qi Wu, Bin ZhuAbstract
We investigate whether GPT-6-Astra, a general-purpose foundation model, can navigate unfamiliar environments using its own perception, reasoning, and decision-making capabilities. Our evaluation focues on zero-shot vision-and-language navigation in continuous environments (VLN-CE) through a minimal interface in the Codex harness, aiming to unleash GPT-6-Astra's full potential for navigation. Using monocular RGB, GPT-6-Astra decides when to observe, how to move, and when to stop, without navigation-specific fine-tuning, a trained waypoint predictor, or a pre-built scene map. Our evaluation yields four main findings. First, \textbf{\textit{GPT-6-Astra achieves strong zero-shot navigation performance using only monocular RGB observations}}. On the common-adopted zero-shot R2R-CE benchmark, ultra reasoning achieves a success rate of \textbf{\textit{79.0\%}}, exceeding the strongest reported zero-shot and supervised success rates by \textbf{\textit{13.0}} and \textbf{\textit{6.9}} percentage points, respectively. Second, \textbf{\textit{GPT-6-Astra advances multi-stage language instructions into coherent, adaptive navigation}} by grounding spatial relations, tracking task progress, and revising its actions. Third, \textbf{\textit{reliable route execution and goal verification remain challenging, even with ultra reasoning}}. Plausible local landmark matches do not consistently lead to correct task completion. Fourth, \textbf{\textit{these capabilities motivate rethinking the role of embodied learning}}. Future VLN research should build on foundation models to advance generalizable and reliable embodied intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29861
PDF
-
Benchmarking and Domain Adaptation of Automatic Speech Recognition for Adolescent Health Communication in Ghanaian Languages
2026-09-24 13:36:38Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu, Paul Azunre, Joel Budu, Lawrence A. Adu-GyamfiAbstract
This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proceeds in three connected stages; First, we benchmark five ASR systems (three language-specific Wav2Vec2 models and two multimodal LLMs, Gemma 3n and Gemma 4) on a general-domain Bible corpus and a Youth Adolescent Sexual and Reproductive Health (ASRH) Domain ASR dataset, using Character and Word Error Rate (CER, WER). Second, guided by the benchmark, we perform supervised domain adaptation: although Gemma 4 was the strongest zero-shot candidate, fine-tuning it proved computationally infeasible, so we pivoted to the compact Qwen3-ASR-0.6B, fine-tuned on a large Ghana Bible corpus (~90k samples) and evaluated strictly on held-out human-collected in-domain audio. Fine-tuning reduced WER on every language, most dramatically for Ewe (WER from 109.3% to 64.8%, a drop of 44.5 pp; CER from 65.1% to 24.9%). Third, we validate the work through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness. KasaHealth was tested by 50 community respondents and achieved a 100% chat-approval rate, a 72% Good-or-Excellent translation rating, and a 92% would-recommend rate, while surfacing the domain gaps that most constrain real-world use. Across all three stages the evidence converges: for these languages the binding constraint is validated in-domain data, not model capability or computation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29798
PDF
-
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
2026-09-24 13:30:02Xinyue Wang, Jiacheng Pang, Kun Zhou, Kexin Zhang, Defu Cao, Fan Feng, Faisal, Songyao Jin, Yan Liu, Biwei HuangAbstract
We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning from one side, continuous-signal perception and zero-shot forecasting from the other, and fuses the two in a shared representation space where both modalities are understood and generated. We study the design choices that make such unified modeling work: where to align the two representation spaces, how to ground language in temporal structure, how to balance understanding with generation, and how to keep joint optimization stable. The resulting recipe combines a unified prompting scheme for diverse time-series and text tasks, stabilized joint training, and supervision from 2.2M curated series--text pairs and 4.9M instruction-tuning samples. Across benchmarks spanning time-series perception, understanding, reasoning, and both context-aided and unimodal forecasting, TimeBraid remains competitive with far larger general-purpose models and task-specific counterparts.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29792
PDF
-
AgriCountDINO: Parameter-Efficient Exemplar-Guided Counting and Localization in Agriculture
2026-09-24 12:13:45Shengjie Guo, Xin Li, Borjana Arsova, Hanno Scharr, Silvio SalviAbstract
Accurate counting and localization of plants and their organs support phenotyping and yield estimation, yet target appearance, scale, and density vary widely across species and imaging conditions. Exemplar boxes specify the target without category-specific retraining, and point predictions identify the individual instances contributing to the count. We introduce AgriCountDINO, a parameter-efficient exemplar-guided framework for joint counting and localization. It conditions frozen multiscale DINOv3 features on exemplar appearance and size, then progressively decodes them into target points. Missed-object recovery extends supervision to targets overlooked by initial matching, and exemplar-adaptive point NMS filters duplicate predictions according to exemplar scale. With 8.4M trainable parameters, approximately one-tenth of TasselNetV4's, AgriCountDINO achieves a three-shot MAE of 11.92 on the TPC-268 benchmark, reducing counting error by 9.7\% while providing individual target locations. Trained only on TPC-268, it achieves a zero-shot MAE of 14.25 on unseen generic object categories in FSC-147, improving upon the best compared zero-shot method by 6.0\% without target-domain training or fine-tuning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29460
PDF
-
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
2026-09-24 12:02:53Xingyu Wu, Yuchen Yan, Zhengxi Lu, Siqi Chen, Xin ZHANG, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Jian Shao, Jun Xiao, Yongliang ShenAbstract
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based paradigm that alternates between a Planner for identifying information needs and a Synthesizer for integrating evidence into an evolving summary state. This design separates planning from synthesis while using the summary as the persistent state of search, reducing both capability coupling and context noise. To train IterSynth effectively, we further introduce Role-Decoupled Policy Optimization (RDPO) for reinforcement learning, which combines terminal outcome rewards with turn-level rubric evaluations and computes role-specific advantages for more precise credit assignment. Experiments on five long-horizon deep-search benchmarks such as BrowseComp and Xbench-DS show that IterSynth-8B achieves an average score of 50.7, surpassing the strongest prior $\leq$8B agent by +4.2\%. Moreover, IterSynth serves as a model-agnostic prompting paradigm, delivering substantial zero-shot gains over ReAct and similar prompting paradigms on frontier proprietary models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29444
PDF
-
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
2026-09-24 11:49:30Ruoqi Guo, Yi Liu, Gelei Deng, Yuekang Li, Lida Zhao, Yutao Wu, Simin Chen, Ying Zhang, Leo Yu ZhangAbstract
Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement learning for calibrated decisions (RLCD), answers many typed questions about one input with calibrated probabilities in a single call. Whether it detects alignment failures has not been measured. We present RLCDAlignBench, which benchmarks Jev on ten alignment failures: sycophancy, jailbreaks, deception, prompt injection, hallucination, privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking. It spans 44 benchmarks and five target models, labelled by each benchmark's scorer and, on two, by humans. Many of these failures are relational, defined against a reference, such as the user's belief or an injected instruction, that the response alone does not reveal. Our key idea is therefore to vary what Jev is asked separately from what it sees: the question's wording and answer type on one side, the fields of the input on the other. A single generic question reaches a median AUROC of 0.886 zero-shot and beats supervised baselines on most benchmarks. Question wording matters little, while context matters more, mostly through fields that encode the label. Jev matches the reference scorer's agreement with human labels, surfaces label defects in existing benchmarks, and costs 63x less than LLM-judge scorers. Code and data: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29429
PDF
-
RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning
2026-09-24 11:22:45Zexi Li, Yehang Zhang, Haojian Huang, Bohan Zhou, Wenqian Li, Chenxu Wang, Yifan Chang, Yangkai Wei, Tianyi Zhang, Ying-Cong Chen, Kaiwen Zhou, Yinchuan Li, James ChengAbstract
General-purpose robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair programs at runtime, incurring latency and entangling reusable mechanisms with task-specific decisions. We introduce RACaP, an agentic framework that moves coding to evolution and uses a Reasoning-and-Acting (ReAct) loop to call frozen, typed Policy APIs at deployment. A two-phase strategy combines capability curriculum learning with autonomous self-evolution to improve the APIs, the ReAct harness, and experience memory. The APIs encode reusable physical mechanisms while exposing arguments for runtime adaptation. ReAct combines task-specific working memory, long-term experience memory, and visual feedback to select actions, verify outcomes, and recover from failures without modifying source code. RACaP achieves 54.4% success on LIBERO-90, 45.0% on zero-shot LIBERO-PRO, and 46.0% on LIBERO-Long, compared with at most 4.0% for CaP baselines on long-horizon tasks. On LIBERO-PRO, it achieves 2.5 times the success rate of CaP baselines and a 1.9-fold speedup in median policy time. For efficient on-robot deployment, rejection-sampled fine-tuning distills GPT-5.6 ReAct decisions into Qwen3-VL-8B-Instruct, yielding a 13.2-fold per-decision inference speedup and reducing repeated physical calls from 16 to 4. These results show that separating reusable code from runtime decisions supports continued evolution, effective transfer, and efficient long-horizon control.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29394
PDF
-
Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models
2026-09-24 10:37:47Youngeun Seol, Jimin Shin, Heeseo Yoon, Uiwon HwangAbstract
Vision-language models such as CLIP achieve strong zero-shot classification, yet under distribution shift, visual embeddings drift from fixed text embeddings. Training-free calibration avoids the per-sample optimization of prompt learning, but prior feature calibration gives each image the full bias of one hard cluster. We propose Domain Recentering with Confidence Calibration (DRC), a training-free method adapting CLIP from a set of unlabeled target images. DRC fits a Gaussian mixture once and subtracts from each embedding a posterior-weighted average of component means. It then removes residual class preference with a log-prior correction, estimating the prior from confidence-weighted predictions. Among compared methods, DRC achieves the highest average accuracy on cross-domain datasets, exceeding zero-shot CLIP by 4.13 and 5.07 points with ViT-B/16 and ResNet-50, with gains over CLIP also holding under ImageNet distribution shifts.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29358
PDF
-
SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking
2026-09-24 09:19:25Aman Arora, Ricard Marsal I Castan, Matteo El-Hariry, Miguel Olivares-MendezAbstract
Termination-based constrained reinforcement learning is attractive for safety-critical robotic deployments: it avoids online optimization at inference, scales easily to many constraints via a single scalar per constraint, and is simpler to implement than commonly used Lagrangian methods. Instead of pricing violations through summed cost penalties, this approach makes violations structurally unprofitable by shortening the effective horizon for each violation. We identify a structural failure mode of this method class on terminal-navigation tasks: reaching a precise goal configuration while satisfying safety constraints that tighten along the final approach. When the goal sits inside the region close to where the constraints become active, the survival-weighted objective makes dwelling outside the goal region strictly preferable to entering, producing high constraint compliance with low task completion. We formalize this pathology and show that a minimal augmentation to off-the-shelf RL algorithms like PPO resolves this ``feasibility collapse''. We empirically demonstrate that adding a dense per-step success signal via an auxiliary value critic improves the task completion rate while maintaining safety-critical constraint compliance. Validation across two representative spacecraft platforms: a 6U-CubeSat spanning the mass and degree-of-freedom envelope of operational proximity operations, and a floating platform testbed for zero-shot sim-to-real transfer in our laboratory, supports the generality of these findings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.06061
PDF
-
Exploring a Single Autoregressive LLM for Unified Target Speech Extraction across Synchronous and Asynchronous Cues
2026-09-24 08:43:45Wenxuan Wu, Shuhan Zhang, Shuai Wang, Haizhou LiAbstract
Target speech extraction (TSE) typically trains a separate extractor per cue, and visual-cue systems often need corruption-matched training to remain robust under visual frame corruption. We show that one autoregressive LLM backbone, TSE-Omni, can serve both temporally synchronous cues (lip movements, co-speech gestures) and asynchronous cues (enrollment audio, text). TSE-Omni is driven by next-token prediction: each step predicts target speech semantic tokens from its own past outputs, which we term self-enrollment, forming a continuous target-speech context initialized by the enrollment cue (asynchronous audio or text, or a short visual prefix). This enables audio-visual compensation: the model uses synchronized visuals when intact and its token history when visual frames are missing. Under clean visuals, TSE-Omni matches strong discriminative and generative baselines (SpeechBERTScore 0.81 on VoxCeleb2 and 0.89 on LRS3 zero-shot) with higher DNSMOS. On the same VoxCeleb2 test set, after a 2 s clean visual start, removing the remaining visual frames leaves SpeechBERTScore at 0.81. It remains usable under sparse overlap and multi-speaker interference, and supports streaming inference. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.29238
PDF
-
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
Abstract
In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions for one synthetic voice rendered in both languages, so the voice cancels and only the accent remains. By a blind LLM accent judge on real dubbing data, reweighting classifier-free guidance between reference and text, and its variants, stay near one identity-accent trade-off curve; we score a method by its speaker similarity above that curve at equal accent ($\Delta$SIM). Across four open TTS models AAG lies above the curve: on OmniVoice $\Delta$SIM is +0.11 to +0.27 on three test sets (accent 3.51 to 4.28 on a 1-5 scale at speaker similarity 0.29, where reweighting keeps 0.02); MaskGCT and CosyVoice 2 also lie above their curves, and on F5-TTS it is more native than any reweighting setting. An LLM-free language-ID measure and a twelve-listener panel agree. A premise test and the reach of a model's own curve indicate in advance whether and roughly how much AAG can gain, predicting the one model where it gains nothing (X-Voice).
Abstract (translated)
URL
https://arxiv.org/abs/2609.29123
PDF
