SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity

NVIDIA's 2:4 Sparse Tensor Cores deliver 2x throughput but demand strict 50% pruning -- a ratio that collapses LLM reasoning accuracy (Qwen3: 54% to 15%). Milder $(2N-2):2N$ patterns (e.g., 6:8, 25% pruning) preserve accuracy yet receive no hardware support, falling back to dense execution without any benefit from sparsity. We present SlideSparse, the first system to unlock Sparse Tensor Core acceleration for the $(2N-2):2N$ model family on commodity GPUs. Our Sliding Window Decomposition reconstructs any $(2N-2):2N$ weight block into $N-1$ overlapping 2:4-compliant windows without any accuracy loss; Activation Lifting fuses the corresponding activation rearrangement into per-token quantization at near-zero cost. Integrated into vLLM, SlideSparse is evaluated across various GPUs (A100, H100, B200, RTX 4090, RTX 5080, DGX-spark), precisions (FP4, INT8, FP8, BF16, FP16), and model families (Llama, Qwen, BitNet). On compute-bound workloads, the measured speedup ratio (1.33x) approaches the theoretical upper-bound $N/(N-1)=4/3$ at 6:8 weight sparsity in Qwen2.5-7B, establishing $(2N-2):2N$ as a practical path to accuracy-preserving LLM acceleration. Code available at https://github.com/bcacdwk/vllmbench.

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity

Semi-structured N:M sparsity and low-bit quantization (e.g., 1.58-bit BitNet) are two promising approaches for improving the efficiency of large language models (LLMs), yet they have largely been studied in isolation. In this work, we investigate their interaction and show that 1.58-bit BitNet is naturally more compatible with N:M sparsity than full-precision models. To study this effect, we propose Sparse-BitNet, a unified framework that jointly applies 1.58-bit quantization and dynamic N:M sparsification while ensuring stable training for the first time. Across multiple model scales and training regimes (sparse pretraining and dense-to-sparse schedules), 1.58-bit BitNet consistently exhibits smaller performance degradation than full-precision baselines at the same sparsity levels and can tolerate higher structured sparsity before accuracy collapse. Moreover, using our custom sparse tensor core, Sparse-BitNet achieves substantial speedups in both training and inference, reaching up to 1.30X. These results highlight that combining extremely low-bit quantization with semi-structured N:M sparsity is a promising direction for efficient LLMs. Code available at https://github.com/AAzdi/Sparse-BitNet

CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis

Foundation models have recently achieved impressive success in computational pathology, demonstrating strong generalization across diverse histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of pathological regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they often fail to capture the coherent tissue architecture beyond isolated patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that automatically partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the most representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.

Learning Native Continuation for Action Chunking Flow Policies

Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries. Real-Time Chunking (RTC) alleviates this issue but is external to the policy, leading to spurious multimodal switching and trajectories that are not intrinsically smooth. We propose Legato, a training-time continuation method for action-chunked flow-based VLA policies. Specifically, Legato initializes denoising from a schedule-shaped mixture of known actions and noise, exposing the model to partial action information. Moreover, Legato reshapes the learned flow dynamics to ensure that the denoising process remains consistent between training and inference under per-step guidance. Legato further uses randomized schedule condition during training to support varying inference delays and achieve controllable smoothness. Empirically, Legato produces smoother trajectories and reduces spurious multimodal switching during execution, leading to less hesitation and shorter task completion time. Extensive real-world experiments show that Legato consistently outperforms RTC across five manipulation tasks, achieving approximately 10% improvements in both trajectory smoothness and task completion time.

Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation

Real-world robotic manipulation demands visuomotor policies capable of robust spatial scene understanding and strong generalization across diverse camera viewpoints. While recent advances in 3D-aware visual representations have shown promise, they still suffer from several key limitations, including reliance on multi-view observations during inference which is impractical in single-view restricted scenarios, incomplete scene modeling that fails to capture holistic and fine-grained geometric structures essential for precise manipulation, and lack of effective policy training strategies to retain and exploit the acquired 3D knowledge. To address these challenges, we present MethodName, a unified representation-policy learning framework for view-generalizable robotic manipulation. MethodName introduces a single-view 3D pretraining paradigm that leverages point cloud reconstruction and feed-forward gaussian splatting under multi-view supervision to learn holistic geometric representations. During policy learning, MethodName performs multi-step distillation to preserve the pretrained geometric understanding and effectively transfer it to manipulation skills. We conduct experiments on 12 RLBench tasks, where our approach outperforms the previous state-of-the-art method by 12.7% in average success rate. Further evaluation on six representative tasks demonstrates strong zero-shot view generalization, with success rate drops of only 22.0% and 29.7% under moderate and large viewpoint shifts respectively, whereas the state-of-the-art method suffers larger decreases of 41.6% and 51.5%.

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked by limited existing verifiable data, where improvements increasingly saturate over prolonged training. To overcome this, we propose Golden Goose, a simple trick to synthesize unlimited RLVR tasks from unverifiable internet text by constructing a multiple-choice question-answering version of the fill-in-the-middle task. Given a source text, we prompt an LLM to identify and mask key reasoning steps, then generate a set of diverse, plausible distractors. This enables us to leverage reasoning-rich unverifiable corpora typically excluded from prior RLVR data construction (e.g., science textbooks) to synthesize GooseReason-0.7M, a large-scale RLVR dataset with over 0.7 million tasks spanning mathematics, programming, and general scientific domains. Empirically, GooseReason effectively revives models saturated on existing RLVR data, yielding robust, sustained gains under continuous RL and achieving new state-of-the-art results for 1.5B and 4B-Instruct models across 15 diverse benchmarks. Finally, we deploy Golden Goose in a real-world setting, synthesizing RLVR tasks from raw FineWeb scrapes for the cybersecurity domain, where no prior RLVR data exists. Training Qwen3-4B-Instruct on the resulting data GooseReason-Cyber sets a new state-of-the-art in cybersecurity, surpassing a 7B domain-specialized model with extensive domain-specific pre-training and post-training. This highlights the potential of automatically scaling up RLVR data by exploiting abundant, reasoning-rich, unverifiable internet text.

Unleashing the Potential of Sparse Attention on Long-term Behaviors for CTR Prediction

In recent years, the success of large language models (LLMs) has driven the exploration of scaling laws in recommender systems. However, models that demonstrate scaling laws are actually challenging to deploy in industrial settings for modeling long sequences of user behaviors, due to the high computational complexity of the standard self-attention mechanism. Despite various sparse self-attention mechanisms proposed in other fields, they are not fully suited for recommendation scenarios. This is because user behaviors exhibit personalization and temporal characteristics: different users have distinct behavior patterns, and these patterns change over time, with data from these users differing significantly from data in other fields in terms of distribution. To address these challenges, we propose SparseCTR, an efficient and effective model specifically designed for long-term behaviors of users. To be precise, we first segment behavior sequences into chunks in a personalized manner to avoid separating continuous behaviors and enable parallel processing of sequences. Based on these chunks, we propose a three-branch sparse self-attention mechanism to jointly identify users' global interests, interest transitions, and short-term interests. Furthermore, we design a composite relative temporal encoding via learnable, head-specific bias coefficients, better capturing sequential and periodic relationships among user behaviors. Extensive experimental results show that SparseCTR not only improves efficiency but also outperforms state-of-the-art methods. More importantly, it exhibits an obvious scaling law phenomenon, maintaining performance improvements across three orders of magnitude in FLOPs. In online A/B testing, SparseCTR increased CTR by 1.72\% and CPM by 1.41\%. Our source code is available at https://github.com/laiweijiang/SparseCTR.

SDP: A Unified Protocol and Benchmarking Framework for Reproducible Wireless Sensing

Learning-based wireless sensing has made rapid progress, yet the field still lacks a unified and reproducible experimental foundation. Unlike computer vision, wireless sensing relies on hardware-dependent channel measurements whose representations, preprocessing pipelines, and evaluation protocols vary significantly across devices and datasets, hindering fair comparison and reproducibility. This paper proposes the Sensing Data Protocol (SDP), a protocol-level abstraction and unified benchmark for scalable wireless sensing. SDP acts as a standardization layer that decouples learning tasks from hardware heterogeneity. To this end, SDP enforces deterministic physical-layer sanitization, canonical tensor construction, and standardized training and evaluation procedures, decoupling learning performance from hardware-specific artifacts. Rather than introducing task-specific models, SDP establishes a principled protocol foundation for fair evaluation across diverse sensing tasks and platforms. Extensive experiments demonstrate that SDP achieves competitive accuracy while substantially improving stability, reducing inter-seed performance variance by orders of magnitude on complex activity recognition tasks. A real-world experiment using commercial off-the-shelf Wi-Fi hardware further illustrating the protocol's interoperability across heterogeneous hardware. By providing a unified protocol and benchmark, SDP enables reproducible and comparable wireless sensing research and supports the transition from ad hoc experimentation toward reliable engineering practice.

AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering

Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate scores, they often yield unstable and hard-to-audit improvement trajectories, making it difficult to guarantee non-regression or to reason about failures across versions. We reframe agent improvement as \textbf{release engineering}: agents are treated as shippable artifacts, and improvement is externalized into a regression-aware release pipeline. We introduce \textbf{AgentDevel}, a release engineering pipeline that iteratively runs the current agent, produces implementation-blind, symptom-level quality signals from execution traces, synthesizes a single release candidate (RC) via executable diagnosis, and promotes it under flip-centered gating. AgentDevel features three core designs: (i) an implementation-blind LLM critic that characterizes failure appearances without accessing agent internals, (ii) script-based executable diagnosis that aggregates dominant symptom patterns and produces auditable engineering specifications, and (iii) flip-centered gating that prioritizes pass to fail regressions and fail to pass fixes as first-class evidence. Unlike population-based search or in-agent self-refinement, AgentDevel maintains a single canonical version line and emphasizes non-regression as a primary objective. Experiments on execution-heavy benchmarks demonstrate that AgentDevel yields stable improvements with significantly fewer regressions while producing reproducible, auditable artifacts. Overall, AgentDevel provides a practical development discipline for building, debugging, and releasing LLM agents as software development.

Multi-AI Agent Framework Reveals the "Oxide Gatekeeper" in Aluminum Nanoparticle Oxidation

Aluminum nanoparticles (ANPs) are among the most energy-dense solid fuels, yet the atomic mechanisms governing their transition from passivated particles to explosive reactants remain elusive. This stems from a fundamental computational bottleneck: ab initio methods offer quantum accuracy but are restricted to small spatiotemporal scales (< 500 atoms, picoseconds), while empirical force fields lack the reactive fidelity required for complex combustion environments. Herein, we bridge this gap by employing a "human-in-the-loop" closed-loop framework where self-auditing AI Agents validate the evolution of a machine learning potential (MLP). By acting as scientific sentinels that visualize hidden model artifacts for human decision-making, this collaborative cycle ensures quantum mechanical accuracy while exhibiting near-linear scalability to million-atom systems and accessing nanosecond timescales (energy RMSE: 1.2 meV/atom, force RMSE: 0.126 eV/Angstrom). Strikingly, our simulations reveal a temperature-regulated dual-mode oxidation mechanism: at moderate temperatures, the oxide shell acts as a dynamic "gatekeeper," regulating oxidation through a "breathing mode" of transient nanochannels; above a critical threshold, a "rupture mode" unleashes catastrophic shell failure and explosive combustion. Importantly, we resolve a decades-old controversy by demonstrating that aluminum cation outward diffusion, rather than oxygen transport, dominates mass transfer across all temperature regimes, with diffusion coefficients consistently exceeding those of oxygen by 2-3 orders of magnitude. These discoveries establish a unified atomic-scale framework for energetic nanomaterial design, enabling the precision engineering of ignition sensitivity and energy release rates through intelligent computational design.