Reference Signal
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References
arXiv:2508.14623v2 Announce Type: replace-cross Abstract: This paper examines the implications of using the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) as both evaluation and training objective in supervised speech separation, when the training references contain noise, as is the case with the de facto benchmark WSJ0-2Mix. A derivation of the SI-SDR with noisy references reveals that noise limits the achievable SI-SDR, or leads to undesired noise in the separated outputs. To address...
Predictive Style Matching: Natural and Robust Humanoid Locomotion
arXiv:2606.07083v1 Announce Type: new Abstract: Reinforcement learning has become the prevailing approach to humanoid locomotion control: policies transfer reliably from simulation to hardware and recover gracefully from disturbances. Motion quality, however, still lags behind: task-only rewards often converge to stiff, asymmetric gaits, while motion imitation methods improve appearance but become more sensitive to external disturbances because reference signals can oppose the transient...
Transferring the driveshaft inertia to the grid via the DC-link in MV drive systems
arXiv:2508.21760v2 Announce Type: replace Abstract: This paper investigates a control approach that renders the driveshaft inertia completely available on the grid side and enhances the fault ride-through behavior of medium-voltage (MV) drive systems. Two main contributions are presented. First, we show how the rotational inertia of the driveline shaft can be synchronously coupled to the grid through a modification of the speed control reference signal and through an adapted DC-link control...
ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation
Announce Type: new Abstract: On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher. In multimodal reasoning, a common extension is to use a privileged teacher that observes training-time-only signals such as reference answers or rationales. However, such answer-side privilege creates a train-test mismatch: the teacher's supervision may depend on signals unavailable to the student, encouraging...
Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
arXiv:2605.19398v3 Announce Type: replace Abstract: Image-to-video models often generate videos that remain overly static, compared to text-to-video models. While prior approaches mitigate this issue by weakening or modifying the image-conditioning signal, they often require additional training or sacrifice fidelity to the reference image. In this work, we identify reference-frame dominance as a key mechanism behind motion suppression.
'Flawless on the outside, flipped within': Detecting hidden defects in 2D dielectrics with light
'Flawless on the outside, flipped within': Detecting hidden defects in 2D dielectrics with light Gaby Clark Scientific Editor Alexander Pol Deputy Editor A material may appear flawless on the surface yet fail to function properly. The cause lies in structural defects hidden within two-dimensional thin films, which are considered key materials for next-generation semiconductor devices.
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry
arXiv:2606.08460v1 Announce Type: cross Abstract: Data-adaptive two-sample testing assesses if two samples come from the same distribution, using a discrepancy learned from the data (e.g., via kernel-based feature representations). Such methods typically rely on data splitting to decouple learning from testing and control type I error. However, this paradigm is ill-suited to few-shot settings with severe sample-size imbalance: abundant reference samples are available, while only a handful of...
A homodyne detection scheme for all-optical photon-photon scattering experiments using 2D detectors
arXiv:2606.07460v1 Announce Type: cross Abstract: Low signal-to-noise ratios are a common problem in experiments attempting to measure photon-photon scattering. In the optical regime, where petawatt lasers with femtosecond pulse durations are used, the large beam sizes cause the major contribution of the background to be spread over up to 100 ps in arrival time, whereas the signal is confined to the femtosecond scale. We present a balanced homodyne measurement scheme, which exploits this...
PriFT: Prior-Support Guided Supervised Fine-Tuning
arXiv:2606.09396v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL. A key limitation is its off-policy objective: SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution, which can lead to overfitting. A recent line of work addresses this...
LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G
Announce Type: replace Abstract: Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency and computational constraints. While Transformer-based models are effective for sequence modeling, their quadratic complexity limits scalability in Near-RT RAN Intelligent Controller (RIC) analytics. This paper investigates a post-Transformer design paradigm for efficient radio telemetry...