Chongqing University

A deep eutectic solvent is a multicomponent hydrogen-bond network of acceptors, donors and solutes, so its solubility cannot be read off the properties of individual constituents. TiNN represents the process in two stages, first forming the acceptor-donor environment and then accommodating the solute, and constrains the temperature and pressure response through a learned free-energy pathway, reaching a test-set $R^2$ of 0.917 on 938 records. In new measurements of glucose, xylan and Kraft lignin in acidic, basic and neutral deep eutectic solvents, TiNN reduces the geometric mean fold error of solubility from more than 23 for COSMO-RS to about 1.5.

A deep eutectic solvent is a multicomponent hydrogen-bond network of acceptors, donors and solutes, so its solubility cannot be read off the properties of individual constituents. TiNN represents the process in two stages, first forming the acceptor-donor environment and then accommodating the solute, and constrains the temperature and pressure response through a learned free-energy pathway, reaching a test-set $R^2$ of 0.917 on 938 records. In new measurements of glucose, xylan and Kraft lignin in acidic, basic and neutral deep eutectic solvents, TiNN reduces the geometric mean fold error of solubility from more than 23 for COSMO-RS to about 1.5.

When a target cell line has no drug measurements, GRAFT links that line's genetic perturbation responses to drug responses measured in source cells and predicts the transcriptional changes a drug would induce. In leave-one-line-out evaluation across five LINCS cancer lines, GRAFT-D0 reached a mean Top20 Pearson correlation of 0.734, above the source mean of 0.493 and the strongest comparator PRnet at 0.689; across five external cellular contexts the equally weighted mean Top20 correlation was 0.606 against a source mean of 0.416. The method rests on a conditioning state built from how the target's genetic responses differ from source references, and predictions still improve when target genetic measurements are few, though gains vary with data quality and source coverage.

When a target cell line has no drug measurements, GRAFT links that line's genetic perturbation responses to drug responses measured in source cells and predicts the transcriptional changes a drug would induce. In leave-one-line-out evaluation across five LINCS cancer lines, GRAFT-D0 reached a mean Top20 Pearson correlation of 0.734, above the source mean of 0.493 and the strongest comparator PRnet at 0.689; across five external cellular contexts the equally weighted mean Top20 correlation was 0.606 against a source mean of 0.416. The method rests on a conditioning state built from how the target's genetic responses differ from source references, and predictions still improve when target genetic measurements are few, though gains vary with data quality and source coverage.

When a target occupies only a small part of the frame, whole-image quality scores are dominated by background, and public benchmarks carry no target-level human opinion scores. BiCG-Net expands the target box into a nested patch sequence, reads it with 11 frozen image quality models, and subtracts two readings from the same image to cancel the target term and teacher bias by construction. On CSIQ and LIVEC the student reaches PLCCs of 0.9009 and 0.9133 against human MOS, above both the best single teacher and the teacher consensus; frozen and transferred zero-shot from CSIQ to LIVEC it reaches 0.8416, 0.1947 above consensus.

When a target occupies only a small part of the frame, whole-image quality scores are dominated by background, and public benchmarks carry no target-level human opinion scores. BiCG-Net expands the target box into a nested patch sequence, reads it with 11 frozen image quality models, and subtracts two readings from the same image to cancel the target term and teacher bias by construction. On CSIQ and LIVEC the student reaches PLCCs of 0.9009 and 0.9133 against human MOS, above both the best single teacher and the teacher consensus; frozen and transferred zero-shot from CSIQ to LIVEC it reaches 0.8416, 0.1947 above consensus.

RGB-D salient object detection has traded the limited receptive field of CNNs against the quadratic cost of Transformers; Mamba models global context at linear cost but flattens 2D features into 1D sequences and loses local structure. LWNet adds a Vision Liquid Time-Constant module on a VMamba backbone, using input-dependent decay to restore detail weakened by scanning, and a cross-modal wavelet fusion that splits RGB and depth features into low- and high-frequency bands for separate alignment. Against 18 methods on STERE, NLPR, NJU2K, DUTLF and SIP, LWNet ranks first on all five datasets.

RGB-D salient object detection has traded the limited receptive field of CNNs against the quadratic cost of Transformers; Mamba models global context at linear cost but flattens 2D features into 1D sequences and loses local structure. LWNet adds a Vision Liquid Time-Constant module on a VMamba backbone, using input-dependent decay to restore detail weakened by scanning, and a cross-modal wavelet fusion that splits RGB and depth features into low- and high-frequency bands for separate alignment. Against 18 methods on STERE, NLPR, NJU2K, DUTLF and SIP, LWNet ranks first on all five datasets.

The end-to-end planner ManeuverFlow organizes candidate trajectories into eight motion maneuvers, generates them in one step, and scores and locally refines them with shared future BEV evidence, reaching 90.58 PDMS and 90.14 EPDMS on NAVSIM v1/v2 navtest.

The end-to-end planner ManeuverFlow organizes candidate trajectories into eight motion maneuvers, generates them in one step, and scores and locally refines them with shared future BEV evidence, reaching 90.58 PDMS and 90.14 EPDMS on NAVSIM v1/v2 navtest.

Isolating the reinforcement-learning-stage parameter update of a language model, keeping only the single dominant direction of each matrix rescaled to the original magnitude, and injecting it into the language modules of a vision-language model improves matched full-update interpolation in 12 of 15 backbone-benchmark comparisons across three model families and five visual-reasoning benchmarks, including an 8.55 percentage-point MathVision gain on the Qwen recipient. Controls show that matching update magnitude or using arbitrary low-rank directions does not reproduce these gains, indicating that what is acquired during post-training and what remains transferable across models are not the same thing.

Isolating the reinforcement-learning-stage parameter update of a language model, keeping only the single dominant direction of each matrix rescaled to the original magnitude, and injecting it into the language modules of a vision-language model improves matched full-update interpolation in 12 of 15 backbone-benchmark comparisons across three model families and five visual-reasoning benchmarks, including an 8.55 percentage-point MathVision gain on the Qwen recipient. Controls show that matching update magnitude or using arbitrary low-rank directions does not reproduce these gains, indicating that what is acquired during post-training and what remains transferable across models are not the same thing.

Through diagnostic analyses, the work locates the bottleneck of vision-language models' spatial weakness in a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning, and introduces 3ViewSense, a framework that grounds spatial reasoning in orthographic views and uses a Simulate-and-Reason mechanism to align egocentric perception with allocentric references, enabling explicit mental rotation and reconstruction; it significantly outperforms existing baselines on spatial reasoning benchmarks, with consistent gains on occlusion-heavy counting and view-consistent spatial reasoning, and also improves the stability and consistency of spatial descriptions.

Through diagnostic analyses, the work locates the bottleneck of vision-language models' spatial weakness in a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning, and introduces 3ViewSense, a framework that grounds spatial reasoning in orthographic views and uses a Simulate-and-Reason mechanism to align egocentric perception with allocentric references, enabling explicit mental rotation and reconstruction; it significantly outperforms existing baselines on spatial reasoning benchmarks, with consistent gains on occlusion-heavy counting and view-consistent spatial reasoning, and also improves the stability and consistency of spatial descriptions.

Researchers developed a flexible wireless wearable stethoscope based on a 25-element circular aluminum nitride (AlN) piezoelectric micromachined ultrasonic transducer (PMUT) array that achieves a packaged sensitivity of −167.5 dB, an operating bandwidth of 10 Hz–10 kHz, and a frequency-response flatness of ±0.5 dB; across multiple participants it acquired heart sounds at five standard auscultation sites with temporal correspondence to reference ECG and chest-motion signals, tracked heart rate continuously during dynamic activities such as walking and stair climbing, and, coupled with a residual neural network, classified five respiratory states (awake, asleep, apnea, rhonchi, and wheeze) with 98.7% accuracy.

Researchers developed a flexible wireless wearable stethoscope based on a 25-element circular aluminum nitride (AlN) piezoelectric micromachined ultrasonic transducer (PMUT) array that achieves a packaged sensitivity of −167.5 dB, an operating bandwidth of 10 Hz–10 kHz, and a frequency-response flatness of ±0.5 dB; across multiple participants it acquired heart sounds at five standard auscultation sites with temporal correspondence to reference ECG and chest-motion signals, tracked heart rate continuously during dynamic activities such as walking and stair climbing, and, coupled with a residual neural network, classified five respiratory states (awake, asleep, apnea, rhonchi, and wheeze) with 98.7% accuracy.