24 articles mentioning stream-qwen3.5-27b
arXiv:2605.08158v3 Announce Type: replace-cross Abstract: Long video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB frames, token growth with frame count, and weak motion perception under sparse keyframe sampling. Exist
arXiv:2606.07036v3 Announce Type: replace-cross Abstract: Synthetic histopathology image generation addresses patient-privacy concerns and the growing data demands of foundation models. Existing state-of-the-art histopathology generative models use pretrained Vision Foundation Models (VFMs) as condi
arXiv:2610.14406v1 Announce Type: cross Abstract: It is widely appreciated that robotic policies require long-term memory to perform complex tasks. However, directly conditioning policies on all past observations leaves policy learning susceptible to learning spurious shortcuts, and introduces large
arXiv:2610.18325v1 Announce Type: cross Abstract: Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model images while maintaining 3D consistency and texture authenticity. Unlike conventi
arXiv:2605.00206v2 Announce Type: replace-cross Abstract: Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables pa
arXiv:2610.09848v1 Announce Type: new Abstract: Inverse design in engineering often runs into a simple problem. Each labeled training sample must be produced through expensive simulation, so building a large dataset is slow and costly. This study addresses that problem for partial inverse design, wh
arXiv:2610.07115v1 Announce Type: cross Abstract: The order in which candidate responses are presented can change an LLM judge's verdict. Detecting such a position flip ordinarily requires judging each pair in both orders, which doubles the number of judgments. We investigate whether residual stream
arXiv:2609.33895v2 Announce Type: replace-cross Abstract: In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These prediction targets are interconvertible and describe the same generative process, yet plain Diffusi
arXiv:2610.02704v1 Announce Type: new Abstract: Time series are produced continuously at enormous scale by industrial equipment, wearables, power grids, and clinical monitors, yet annotation remains manual, expensive, and expert-dependent. The binding constraint in large-scale time series analytics
arXiv:2609.35579v2 Announce Type: replace Abstract: Residual stream pruning methods reduce inference cost by shrinking the model's hidden dimension, but existing approaches typically choose these dimensions by minimizing activation reconstruction error. This criterion implicitly treats all perturbat
arXiv:2609.38802v1 Announce Type: new Abstract: Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses of repetitive generation have identified strongly activated features in intermediate and late layers.
arXiv:2609.39005v1 Announce Type: new Abstract: Emergency managers need to know where floodwater is, how deep it is, and how it will change over the coming hours across an entire river basin. During a flood, however, real-time measurements come from only a handful of stream gauges, and high-resoluti
arXiv:2601.02641v2 Announce Type: replace Abstract: Despite its efficiency, there has been little research on the practical aspects required for real-world deployment of on-device AI models, such as the device's CPU utilization and thermal conditions. In this paper, through extensive experiments, we
arXiv:2609.32551v2 Announce Type: replace-cross Abstract: Text-conditioned human-object interaction (HOI) generation requires body motion, object trajectories & rotations, and hand articulation to remain coordinated. These components differ in scale and dynamics, but must agree on contact, relative
arXiv:2609.31098v1 Announce Type: new Abstract: We introduce \emph{effective depth} ($\Deff$), a scalar diagnostic that treats the layer-wise residual stream of a transformer as a discrete-time process, measures how representation similarity decays with layer distance, and aggregates that profile in
arXiv:2609.28809v1 Announce Type: new Abstract: Mechanistic interpretability seeks to make verifiable statements about the internal behavior of large language models (LLMs). Many interpretability techniques struggle to scale with the increasing size and depth of architectures. Our solution to this i
arXiv:2406.04814v4 Announce Type: replace-cross Abstract: Video diffusion models can enable embodied agents to anticipate plausible futures from the recent past, but they are typically trained offline on curated datasets--a mismatch with the agents' learning setup at deployment: online, from a singl
arXiv:2609.22620v1 Announce Type: new Abstract: Scanned mail, uploaded PDFs, and consolidated attachments often arrive as page streams that must be split into individual documents before downstream classification, extraction, or routing. Zero-shot large language models can detect document boundaries
arXiv:2609.23659v1 Announce Type: new Abstract: Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create strong machine-learning shortcuts. We introduce ETH-TraceBench, a benchmark for evaluating Ethereum
arXiv:2605.24696v3 Announce Type: replace-cross Abstract: Streaming intrusion-detection studies assemble evaluation streams from network captures by interleaving capture days, pooling captures, or replaying records round robin. We show on two benchmarks that this assembly is an uncontrolled experime
arXiv:2609.16312v1 Announce Type: cross Abstract: One-to-many machine translation (MT) is computationally expensive for autoregressive (AR) systems, which suffer from linear latency scaling with both sequence length and the number of target languages. We explore how diffusion can enable multilingual
arXiv:2609.12793v1 Announce Type: new Abstract: Stock price prediction remains challenging due to the non-stationary and noisy nature of financial time series. Existing deep learning models often rely on rigid decision-level fusion, ad hoc hyperparameter tuning, and compressed final-layer outputs, c
arXiv:2609.09432v1 Announce Type: cross Abstract: Real-world datasets often exhibit evolving distributions, known as concept drift. Ignoring drift degrades predictive performance, while reliance on fixed hyperparameters further limits model adaptability under changing conditions. Adaptive learning a
arXiv:2512.22007v2 Announce Type: replace Abstract: DuaDeep-SeqAffinity is a sequence-only deep learning framework that predicts antibody--antigen binding affinity directly from primary amino acid sequences, avoiding the cost and scarcity of resolved three-dimensional structures. The antigen and the