Zihan Zheng, Tianle Cui, Taoran Wang, Fengtao Wang, Jiahui Pan, Lewei He, Qianglong Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Neural Radiance Field (NeRF)-based volumetric video has revolutionized visual media by delivering photorealistic Free-Viewpoint Video (FVV) experiences that provide audiences with unprecedented immersion and interactivity. However, the substantial data volumes pose significant challenges for storage and transmission. Existing solutions typically optimize NeRF representation and compression independently or focus on a single fixed rate-distortion (RD) tradeoff. In this paper, we propose VRVVC, a novel end-to-end joint optimization variable-rate framework for volumetric video compression that achieves variable bitrates using a single model while maintaining superior RD performance. Specifically, VRVVC introduces a compact tri-plane implicit residual representation for inter-frame modeling of long-duration dynamic scenes, effectively reducing temporal redundancy. We further propose a variable-rate residual representation compression scheme that leverages a learnable quantization and a tiny MLP-based entropy model. This approach enables variable bitrates through the utilization of predefined Lagrange multipliers to manage the quantization error of all latent representations. Finally, we present an end-to-end progressive training strategy combined with a multi-rate-distortion loss function to optimize the entire framework. Extensive experiments demonstrate that VRVVC achieves a wide range of variable bitrates within a single model and surpasses the RD performance of existing methods across various datasets.

One of the research focuses of large language models (LLMs) is the ability to generate action plans.Recent studies have revealed that the performance of LLMs can be significantly improved by integrating external tools.Based on this, we propose a benchmark framework called PlanningArena, which aims to simulate real application scenarios and provide a series of apps and API tools that may be involved in the actual planning process.This framework adopts a modular task structure and combines user portrait analysis to evaluate the ability of LLMs in correctly selecting tools, logical reasoning in complex scenarios, and parsing user information.In addition, we deeply diagnose the task execution effect of LLMs from both macro and micro levels.The experimental results show that even the most outstanding GPT-4o and DeepSeekV3 models only achieved a total score of 56.5% and 41.9% in PlanningArena, respectively, indicating that current LLMs still face challenges in logical reasoning, context memory, and tool calling when dealing with different structures, scenarios, and their complexity.Through this benchmark, we further explore the path to optimize LLMs to perform planning tasks.

3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences. However, the vast number of Gaussians and their associated attributes poses significant challenges for storage and transmission. Existing methods typically handle dynamic 3DGS representation and compression separately, neglecting motion information and the rate-distortion (RD) trade-off during training, leading to performance degradation and increased model redundancy. To address this gap, we propose 4DGC, a novel rate-aware 4D Gaussian compression framework that significantly reduces storage size while maintaining superior RD performance for FVV. Specifically, 4DGC introduces a motion-aware dynamic Gaussian representation that utilizes a compact motion grid combined with sparse compensated Gaussians to exploit inter-frame similarities. This representation effectively handles large motions, preserving quality and reducing temporal redundancy. Furthermore, we present an end-to-end compression scheme that employs differentiable quantization and a tiny implicit entropy model to compress the motion grid and compensated Gaussians efficiently. The entire framework is jointly optimized using a rate-distortion trade-off. Extensive experiments demonstrate that 4DGC supports variable bitrates and consistently outperforms existing methods in RD performance across multiple datasets.

Recent reports claim that large language models (LLMs) now outperform elite humans in competitive programming. Drawing on knowledge from a group of medalists in international algorithmic contests, we revisit this claim, examining how LLMs differ from human experts and where limitations still remain. We introduce LiveCodeBench Pro, a benchmark composed of problems from Codeforces, ICPC, and IOI that are continuously updated to reduce the likelihood of data contamination. A team of Olympiad medalists annotates every problem for algorithmic categories and conducts a line-by-line analysis of failed model-generated submissions. Using this new data and benchmark, we find that frontier models still have significant limitations: without external tools, the best model achieves only 53\% pass@1 on medium-difficulty problems and 0\% on hard problems, domains where expert humans still excel. We also find that LLMs succeed at implementation-heavy problems but struggle with nuanced algorithmic reasoning and complex case analysis, often generating confidently incorrect justifications. High performance appears largely driven by implementation precision and tool augmentation, not superior reasoning. LiveCodeBench Pro thus highlights the significant gap to human grandmaster levels, while offering fine-grained diagnostics to steer future improvements in code-centric LLM reasoning.

Achieving seamless viewing of high-fidelity volumetric video, comparable to 2D video experiences, remains an open challenge. Existing volumetric video compression methods either lack the flexibility to adjust quality and bitrate within a single model for efficient streaming across diverse networks and devices, or struggle with real-time decoding and rendering on lightweight mobile platforms. To address these challenges, we introduce 4DGCPro, a novel hierarchical 4D Gaussian compression framework that facilitates real-time mobile decoding and high-quality rendering via progressive volumetric video streaming in a single bitstream. Specifically, we propose a perceptually-weighted and compression-friendly hierarchical 4D Gaussian representation with motion-aware adaptive grouping to reduce temporal redundancy, preserve coherence, and enable scalable multi-level detail streaming. Furthermore, we present an end-to-end entropy-optimized training scheme, which incorporates layer-wise rate-distortion (RD) supervision and attribute-specific entropy modeling for efficient bitstream generation. Extensive experiments show that 4DGCPro enables flexible quality and variable bitrate within a single model, achieving real-time decoding and rendering on mobile devices while outperforming existing methods in RD performance across multiple datasets.

3D Gaussian Splatting (3DGS) has recently enabled real-time photorealistic rendering in compact scenes, but scaling to large urban environments introduces severe aliasing artifacts and optimization instability, especially under high-resolution (e.g., 4K) rendering. These artifacts, manifesting as flickering textures and jagged edges, arise from the mismatch between Gaussian primitives and the multi-scale nature of urban geometry. While existing "divide-and-conquer" pipelines address scalability, they fail to resolve this fidelity gap. In this paper, we propose PrismGS, a physically-grounded regularization framework that improves the intrinsic rendering behavior of 3D Gaussians. PrismGS integrates two synergistic regularizers. The first is pyramidal multi-scale supervision, which enforces consistency by supervising the rendering against a pre-filtered image pyramid. This compels the model to learn an inherently anti-aliased representation that remains coherent across different viewing scales, directly mitigating flickering textures. This is complemented by an explicit size regularization that imposes a physically-grounded lower bound on the dimensions of the 3D Gaussians. This prevents the formation of degenerate, view-dependent primitives, leading to more stable and plausible geometric surfaces and reducing jagged edges. Our method is plug-and-play and compatible with existing pipelines. Extensive experiments on MatrixCity, Mill-19, and UrbanScene3D demonstrate that PrismGS achieves state-of-the-art performance, yielding significant PSNR gains around 1.5 dB against CityGaussian, while maintaining its superior quality and robustness under demanding 4K rendering.

This article introduces a successive approximation register (SAR) analog-to-digital converter (ADC) that utilizes a foreground capacitor mismatch self-calibration method. The proposed floating operation puts the uncalibrated high-bit capacitor into the floating state, preventing the sub-ADC from saturating caused by comparator static offset during the calibration process. To address the random mismatch of the LSB capacitors and improve the calibration accuracy, this article employs round-robin grouping of eight sets of LSB capacitors. In addition, a precharged bootstrapped switch is proposed to achieve high sampling linearity with low power consumption and area overhead. An anti-interference custom-designed 0.5-fF capacitor structure is suggested for binary-weighted capacitor mismatch of capacitive DAC (CDAC). Furthermore, the circuit implementation of the comparator utilized by ADC is also discussed. The prototype was fabricated in a 180-nm CMOS process with a 1.8-V supply and achieved spurious-free dynamic ranges of 108.9 and 92.38 dB at an input frequency of 1 kHz while operating at sampling rates of 100 kS/s and 1 MS/s, respectively. The prototype consumes 6.745 mW and occupies 0.91$\text {mm}^{2}$.

Neural Radiance Field (NeRF) excels in photo-realistically static scenes, inspiring numerous efforts to facilitate volumetric videos. However, rendering dynamic and long-sequence radiance fields remains challenging due to the significant data required to represent volumetric videos. In this paper, we propose a novel end-to-end joint optimization scheme of dynamic NeRF representation and compression, called JointRF, thus achieving significantly improved quality and compression efficiency against the previous methods. Specifically, JointRF employs a compact residual feature grid and a coefficient feature grid to represent the dynamic NeRF. This representation handles large motions without compromising quality while concurrently diminishing temporal redundancy. We also introduce a sequential feature compression subnetwork to further reduce spatial-temporal redundancy. Finally, the representation and compression subnetworks are end-to-end trained combined within the JointRF. Extensive experiments demonstrate that JointRF can achieve superior compression performance across various datasets.

Volumetric video based on Neural Radiance Field (NeRF) holds vast potential for various 3D applications, but its substantial data volume poses significant challenges for compression and transmission. Current NeRF compression lacks the flexibility to adjust video quality and bitrate within a single model for various network and device capacities. To address these issues, we propose HPC, a novel hierarchical progressive volumetric video coding framework achieving variable bitrate using a single model. Specifically, HPC introduces a hierarchical representation with a multi-resolution residual radiance field to reduce temporal redundancy in long-duration sequences while simultaneously generating various levels of detail. Then, we propose an end-to-end progressive learning approach with a multi-rate-distortion loss function to jointly optimize both hierarchical representation and compression. Our HPC trained only once can realize multiple compression levels, while the current methods need to train multiple fixed-bitrate models for different rate-distortion (RD) tradeoffs. Extensive experiments demonstrate that HPC achieves flexible quality levels with variable bitrate by a single model and exhibits competitive RD performance, even outperforming fixed-bitrate models across various datasets.

Advances in single-cell sequencing and data analysis have made it possible to infer biological trajectories spanning heterogeneous cell populations based on transcriptome variation. These trajectories yield a wealth of novel insights into dynamic processes such as development and differentiation. However, trajectory analysis relies on an assumption of trajectory continuity, and experimental limitations preclude some real-world scenarios from meeting this condition. The current lack of assessment metrics makes it difficult to ascertain if/when a given trajectory deviates from continuity, and what impact such a divergence would have on inference accuracy is unclear. By analyzing simulated breaks introduced into in silico and real single-cell data, we found that discontinuity caused precipitous drops in the accuracy of trajectory inference. We then generate a simple scoring algorithm for assessing trajectory continuity, and found that continuity assessments in real-world cases of intestinal stem cell development and CD8 + T cells differentiation efficiently identifies trajectories consistent with empirical knowledge. This assessment approach can also be used in cases where a priori knowledge is lacking to screen a pool of inferred lineages for their adherence to presumed continuity, and serve as a means for weighing higher likelihood trajectories for validation via empirical studies, as exemplified by our case studies in psoriatic arthritis and acute kidney injury. This tool is freely available through github at qingshanni/scEGRET.

Recent advances in bioinformatics analyses have led to the development of novel tools enabling the capture and trajectory mapping of single-cell RNA sequencing (scRNAseq) data. However, there is a lack of methods to assess the contributions of biological pathways and transcription factors to an overall developmental trajectory mapped from scRNAseq data. In this manuscript, we present a simplified approach for trajectory inference of pathway significance (TIPS) that leverages existing knowledgebases of functional pathways and other gene lists to provide further mechanistic insights into a biological process. TIPS identifies key pathways which contribute to a process of interest, as well as the individual genes that best reflect these changes. TIPS also provides insight into the relative timing of pathway changes, as well as a suite of visualizations to enable simplified data interpretation of scRNAseq libraries generated using a wide range of techniques. The TIPS package can be run through either a web server or downloaded as a user-friendly GUI run in R, and may serve as a useful tool to help biologists perform deeper functional analyses and visualization of their single-cell data.

In this paper, we propose a novel Deep Reinforcement Learning framework for news recommendation. Online personalized news recommendation is a highly challenging problem due to the dynamic nature of news features and user preferences. Although some online recommendation models have been proposed to address the dynamic nature of news recommendation, these methods have three major issues. First, they only try to model current reward (e.g., Click Through Rate). Second, very few studies consider to use user feedback other than click / no click labels (e.g., how frequent user returns) to help improve recommendation. Third, these methods tend to keep recommending similar news to users, which may cause users to get bored. Therefore, to address the aforementioned challenges, we propose a Deep Q-Learning based recommendation framework, which can model future reward explicitly. We further consider user return pattern as a supplement to click / no click label in order to capture more user feedback information. In addition, an effective exploration strategy is incorporated to find new attractive news for users. Extensive experiments are conducted on the offline dataset and online production environment of a commercial news recommendation application and have shown the superior performance of our methods.

The Cancer Genome Atlas project has generated multi-dimensional and highly integrated genomic data from a large number of patient samples with detailed clinical records across many cancer types, but it remains unclear how to best integrate the massive amount of genomic data into clinical practice. We report here our methodology to build a multi-dimensional subnetwork atlas for cancer prognosis to better investigate the potential impact of multiple genetic and epigenetic (gene expression, copy number variation, microRNA expression and DNA methylation) changes on the molecular states of networks that in turn affects complex cancer survivorship. We uncover an average of 38 novel subnetworks in the protein-protein interaction network that correlate with prognosis across four prominent cancer types. The clinical utility of these subnetwork biomarkers was further evaluated by prognostic impact evaluation, functional enrichment analysis, drug target annotation, tumor stratification and independent validation. Some pathways including the dynactin, cohesion and pyruvate dehydrogenase-related subnetworks are identified as promising new targets for therapy in specific cancer types. In conclusion, this integrative analysis of existing protein interactome and cancer genomics data allows us to systematically dissect the molecular mechanisms that underlie unexpected outcomes for cancer, which could be used to better understand and predict clinical outcomes, optimize treatment and to provide new opportunities for developing therapeutics related to the subnetworks identified.