Diffusion transformers demonstrate significant potential for various generation tasks but are challenged by high computational cost. Recently, feature caching methods have been introduced to improve inference efficiency by storing features at certain timesteps and reusing them at subsequent timesteps. However, their effectiveness is limited as they rely only on choosing between cached features and performing model inference. Motivated by high cosine similarity between features across consecutive timesteps, we propose a cache-based framework that reuses features and selectively adapts them through linear modulation. In our framework, the selection is performed via a modulation gate, and both the gate and modulation parameters are learned. Extensive experiments show that our method achieves similar generation performance to the original sampler while requiring significantly less computation. For example, FLOPs and inference latency are reduced by 2.93 and 2.15 for DiT-XL/2 and by 2.83 and 1.50 for PixArt-α, respectively. We find that modulation is effective when applied to as little as 2% of layers, resulting in negligible computation overhead.

Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient sparse attention that replaces full attention at both training and inference. In VSA, a lightweight coarse stage pools tokens into tiles and identifies high-weight critical tokens; a fine stage computes token-level attention only inside those tiles subjecting to block computing layout to ensure hard efficiency. This leads to a single differentiable kernel that trains end-to-end, requires no post-hoc profiling, and sustains 85% of FlashAttention3 MFU. We perform a large sweep of ablation studies and scaling-law experiments by pretraining DiTs from 60M to 1.4B parameters. VSA reaches a Pareto point that cuts training FLOPS by 2.53 with no drop in diffusion loss.

VVideoidelaro Inputge language models (video LLMs) excel at video comprehension but face Vision Encodersignificant computational inefficiency due to redundant video tokens.

Visual navigation is essential for robotics and embodied AI. However, existing foundation models, particularly those with transformer decoders, suffer from high computational overhead and lack interpretability, limiting their deployment in resource-tight scenarios. To address this, we propose DynaNav, a Dynamic Visual Navigation framework that adapts feature and layer selection based on scene complexity. It employs a trainable hard feature selector for sparse operations, enhancing efficiency and interpretability. Additionally, we integrate feature selection into an early-exit mechanism, with Bayesian Optimization determining optimal exit thresholds to reduce computational cost. Extensive experiments in real-world-based datasets and simulated environments demonstrate the effectiveness of DynaNav. Compared to ViNT, DynaNav achieves a 2.26 reduction in FLOPs, 42.3% lower inference time, and 32.8% lower memory usage, while improving navigation performance across four public datasets.

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges, first, a narrow focus on singlestep tasks that overlooks the complexity of multi-step web interactions, and second, the high compute costs required to post-train LLM-based web agents. To address this, we present the first statistically grounded study on compute allocation for LLM web-agent post-training. Our approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate a Llama 3.3 70B teacher via SFT, followed by on-policy reinforcement learning. We find this process highly sensitive to hyperparameter choices in setting where exhaustive sweeps are impractical. To spare others from expensive trial-and-error, we sample 1,370 configurations and use bootstrapping to estimate effective hyperparameters. Our results show that combining SFT with on-policy RL consistently outperforms either approach alone on both WorkArena and MiniWob++. Further, this strategy only requires 55% of the compute to match the peak of pure SFT on MiniWob++, pushing the compute-performance Pareto frontier and is the only strategy that can close the gap with closed-source models.

Scaling laws for large language models (LLMs) predict model performance based on parameters like size and training data. However, differences in training configurations and data processing across model families lead to significant variations in benchmark performance, making it difficult for a single scaling law to generalize across all LLMs. On the other hand, training family-specific scaling laws requires training models of varying sizes for every family. In this work, we propose Skills Scaling Laws (SSLaws, pronounced as Sloth), a novel scaling law that leverages publicly available benchmark data and assumes LLM performance is driven by low-dimensional latent skills, such as reasoning and instruction following. These latent skills are influenced by computational resources like model size and training tokens, but with varying efficiencies across model families. Sloth exploits correlations across benchmarks to provide more accurate and interpretable predictions while alleviating the need to train multiple LLMs per family. We present both theoretical results on parameter identification and empirical evaluations on 12 prominent benchmarks, from Open LLMLeaderboard v1/v2, demonstrating that Slothpredicts LLM performance accurately and offers insights into scaling behaviors for complex downstream tasks, increased test-time compute, and compute-optimal scaling of skills.

Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, despite their widespread deployment in inference services such as Midjourney, concerns about the potential leakage of sensitive information in uploaded user prompts have arisen. Existing solutions either lack rigorous privacy guarantees or fail to strike an effective balance between utility and efficiency. To bridge this gap, we propose ObCLIP, a plug-and-play safeguard that enables oblivious clouddevice hybrid generation. By oblivious, each input prompt is transformed into a set of semantically similar candidate prompts that differ only in sensitive attributes (e.g., gender, ethnicity).

Surface electromyography (sEMG) at the wrists could enable natural, keyboard free text entry, yet the state of the art emg2qwerty baseline still misrecognizes 51.8\% of characters zero shot on unseen users and 7.0\% after user specific fine tuning. We trace much of these errors to mismatched cross user signal statistics, fragile reliance on high order feature dependencies, and the absence of architectural inductive biases aligned with the bilateral nature of typing. To address these issues, we introduce three simple modifications: (i) Rolling Time Normalization which adaptively aligns input distributions across users; (ii) Aggressive Channel Masking, which encourages reliance on low order feature combinations more likely to generalize across users; and (iii) a Split and Share encoder that processes each hand independently with weight shared streams to reflect the bilateral symmetry of the neuromuscular system. Combined with a five fold reduction in spectral resolution (33$\rightarrow$6 frequency bands), these components yield a compact Split-and-Share model, SplashNet mini, which uses only the parameters and 0.6 the FLOPs of the baseline while reducing character error rate (CER) to 36.4\% zero shot and 5.9\% after fine tuning. An upscaled variant, SplashNet ( parameters, 1.15 FLOPs of the baseline), further lowers error to 35.7\% and 5.5\%, representing 31\% and 21\% relative improvements in the zero-shot and finetuned settings, respectively. SplashNet therefore establishes a new state-of-the-art without requiring additional data.

Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy. This leads to two symmetric failure modes: easy queries produce near-zero advantage because the policy already solves them, while unsolvable queries produce no signal because the policy never solves them. Both regimes waste training FLOPs without contributing to a learning gradient. We introduce sorted Group Policy Optimization (sGPO), a compute-efficient strategy that trades a small budget of inference FLOPs for a large reduction in wasted training FLOPs. The key insight is that cheap inference compute can serve as a single offline proxy for query difficulty. By generating a small batch of parallel samples per query under the initial policy, we obtain a model-aware empirical success rate. This motivates setting the training rollout group size to the inverse of this success rate, a practical rule that maximizes sample efficiency by extracting the most advantage per generated rollout. This single profiling pass simultaneously drives data filtering (removing trivial queries and sub-sampling unsolvable ones), adaptive group size allocation, and curriculum construction (scheduling queries from easy to hard). sGPO matches or exceeds baseline performance while reducing total training compute by a factor of three, with the upfront inference profiling cost included.