Knowledge catalogue
arXiv:2609.01217v1 Announce Type: new Abstract: Despite their strong performance, large language models remain highly sensitive to prompt formulation. Prior work addresses this through refined data co
arXiv:2609.00588v1 Announce Type: new Abstract: Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, are widely used in modern neural machine translation
arXiv:2603.05887v2 Announce Type: replace-cross Abstract: Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation i
arXiv:2609.00342v1 Announce Type: new Abstract: Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distrib
arXiv:2609.01343v1 Announce Type: new Abstract: Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating archite
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily f
arXiv:2609.00658v1 Announce Type: new Abstract: Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Ye
arXiv:2609.00455v1 Announce Type: new Abstract: Large language models (LLMs) are being used as policies for autonomous decision-making and planning in many domains. Despite their strong reasoning capa
arXiv:2609.00665v1 Announce Type: new Abstract: Edge-AI model selection is commonly driven by one isolated metric - accuracy, latency, memory, energy, or safety, even though a deployable language mode
arXiv:2609.00498v1 Announce Type: new Abstract: Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior
arXiv:2609.01420v1 Announce Type: new Abstract: Cooperation in multi-UAV systems requires reliable relative perception so that follower vehicles can maintain formation and continue their mission safel
We benchmark Qwen3.6-35B-A3B on an M5 Max MacBook Pro. Across ten prompt lengths and ten decode contexts, Lily was faster than MLX-LM, averaging 1.23× higher prefill throughput and 1.35× higher decode
arXiv:2606.21704v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces infla
arXiv:2609.01455v1 Announce Type: cross Abstract: Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior
arXiv:2609.00284v1 Announce Type: cross Abstract: Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traffi
arXiv:2609.00309v1 Announce Type: cross Abstract: AI compute verification is one of the first tangible and tractable points for international policy aimed at AI governance. Determining whether frontie
arXiv:2608.29291v1 Announce Type: new Abstract: Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generatio
arXiv:2608.29937v1 Announce Type: new Abstract: Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space. LaWAM established this formul
arXiv:2608.29262v1 Announce Type: cross Abstract: Decision trees are attractive for tabular prediction tasks because each prediction follows an interpretable sequence of feature-threshold tests. Under
arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is
arXiv:2608.29478v1 Announce Type: cross Abstract: Scholarly work which aims to describe potential societal impacts (e.g., risks) of proliferating technology (especially related to artificial intellige
arXiv:2606.15017v2 Announce Type: replace Abstract: Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume t
arXiv:2602.08727v2 Announce Type: replace-cross Abstract: Undersampled CT volumes minimize acquisition time and radiation exposure but introduce artifacts degrading image quality and diagnostic utilit
arXiv:2608.29111v1 Announce Type: cross Abstract: Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private d
arXiv:2608.28798v1 Announce Type: new Abstract: Stereoscopic omnidirectional images (SOIs) have provided users with newly immersive quality of experience in virtual reality environments. However, deve
arXiv:2608.30731v1 Announce Type: cross Abstract: Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challeng
arXiv:2608.30242v1 Announce Type: new Abstract: While visual navigation has advanced through imitation learning from cross-platform demonstrations, fully leveraging such data remains challenging. Firs
arXiv:2608.30922v1 Announce Type: new Abstract: Masked diffusion language models predict tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel token refine
arXiv:2603.26509v2 Announce Type: replace Abstract: Computed tomography (CT) provides rich 3D anatomical detail but is often constrained by high radiation exposure, substantial costs, and limited avai
arXiv:2608.31170v1 Announce Type: new Abstract: While WhisperX accelerates speech transcription via intra-audio batching, it isolates audio segments, losing the historical context needed for coherent
DeepSeek V4 Flash now comes with native vision on Fireworks. Available now on serverless and priority tiers. Better benchmarks than the text-only 0731 version at the same low price: 0.22 input / 0.66
arXiv:2608.29507v1 Announce Type: cross Abstract: Diffusion models are increasingly used not only for sampling from learned data distributions, but also for generating samples that optimize task-speci
arXiv:2608.30877v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have demonstrated exceptional performance in protein-ligand interaction prediction, but state-of-the-art
arXiv:2601.06644v2 Announce Type: replace-cross Abstract: The real-world information sources are inherently multilingual, which naturally raises a question about whether language models can synthesize
arXiv:2608.28730v1 Announce Type: cross Abstract: Latest JPEG restoration systems achieve strong quality with large models, yet often remain too slow and expensive for efficient on-device deployment.
arXiv:2608.28678v1 Announce Type: new Abstract: Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized im
arXiv:2608.29311v1 Announce Type: new Abstract: Classic Formal Concept Analysis (FCA) primarily focuses on the positive relationships between objects and attributes and does not have mechanisms for ha
arXiv:2608.29590v1 Announce Type: new Abstract: We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely o
arXiv:2608.29924v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. We
arXiv:2608.29193v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) can assign similar confidence to answers that fail for different reasons. We propose HalluPrism, a behavioral d
arXiv:2608.29088v1 Announce Type: new Abstract: Multimodal question answering remains sensitive to noisy, incomplete, and weakly grounded evidence. Long unstructured contexts can introduce redundancy
ZS Associates built a security‑hardened Amazon SageMaker Studio environment that grants developers ad‑hoc analytics access while meeting strict compliance standards for regulated industries, such as h
arXiv:2607.15542v2 Announce Type: replace Abstract: On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (VB
arXiv:2608.29168v1 Announce Type: new Abstract: The LLM-as-a-Judge paradigm has emerged as a scalable alternative to human evaluation. However, single-model judges are limited by their inherent model
arXiv:2601.07794v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly evaluated on their ability to perform multi-hop reasoning, i.e., to combine multiple pieces of i
arXiv:2606.17511v2 Announce Type: replace-cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not
arXiv:2608.29677v1 Announce Type: cross Abstract: Despite rapid advances in MIS, fair and reproducible comparisons of segmentation models remain challenging due to heterogeneous datasets, inconsistent
arXiv:2608.30903v1 Announce Type: new Abstract: Dynamic stance classification models how a reply responds to its direct parent message, rather than how a post relates to a fixed topic. Existing work h
arXiv:2608.30563v1 Announce Type: new Abstract: Multimodal Emotion Recognition (MER) systems often suffer from missing modalities in real-world scenarios. Existing methods usually generate, align, or
arXiv:2510.01159v3 Announce Type: replace Abstract: Learning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applicati
arXiv:2603.02482v2 Announce Type: replace-cross Abstract: Safety evaluation of multimodal large language models requires tracking not only whether an attack succeeds, but also how the interaction unfo
arXiv:2608.31036v1 Announce Type: new Abstract: While low-rank adaptation (LoRA) is widely used for parameter-efficient model adaptation, how to regularize its training dynamics for stable and effecti
arXiv:2608.29136v1 Announce Type: cross Abstract: We ask whether a model protects a user in the same way when that user speaks rather than types. Using a single distress vignette---a physical injury o
arXiv:2608.29913v1 Announce Type: new Abstract: TinyML includes the implementation of machine learning on devices with limited memory and computing resources. With the development of technology, AI sy
arXiv:2608.29943v1 Announce Type: cross Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to r
arXiv:2608.31096v1 Announce Type: new Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while pr
arXiv:2608.30229v1 Announce Type: new Abstract: Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are inter
arXiv:2608.30400v1 Announce Type: new Abstract: High-dynamic-range (HDR) images, with their rich tone and detail reproduction, hold significant potential to enhance computer vision systems, particular
arXiv:2608.30617v1 Announce Type: new Abstract: Reconstructing editable Computer-Aided Design (CAD) models from images is essential for downstream modification, manufacturing, and design reuse. Howeve
arXiv:2608.28963v1 Announce Type: cross Abstract: The number of knowledge graph databases has increased significantly with the proliferation of knowledge graph technologies. Knowledge graphs enable th