Knowledge catalogue
arXiv:2605.07075v1 Announce Type: new Abstract: The open-source model ecosystem now contains hundreds of thousands of pretrained models, yet picking the best model for a new dataset is increasingly in
arXiv:2605.07800v1 Announce Type: new Abstract: Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions spe
arXiv:2508.10016v3 Announce Type: replace Abstract: Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse heterogeneous modalities, which incurs substantia
arXiv:2605.04449v1 Announce Type: new Abstract: Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models
arXiv:2603.06542v2 Announce Type: replace-cross Abstract: Conversational generative AI is increasingly explored in healthcare, where models must integrate heterogeneous patient signals and support div
arXiv:2605.04617v1 Announce Type: new Abstract: Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time a
arXiv:2605.04070v1 Announce Type: cross Abstract: Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversig
arXiv:2605.03354v1 Announce Type: new Abstract: Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information ne
arXiv:2412.13235v4 Announce Type: replace Abstract: The logic-constrained shortest path problem (LCSPP) combines a one-to-one shortest path problem with satisfiability constraints imposed on the routi
arXiv:2601.06543v2 Announce Type: replace Abstract: Queueing simulation studies often require substantial manual effort to translate conceptual system descriptions into executable programs and to veri
arXiv:2605.03348v1 Announce Type: new Abstract: We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of en
arXiv:2605.02443v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to
arXiv:2605.00043v1 Announce Type: cross Abstract: Big data platforms are widely used in modern enterprises, and an in-production intelligent assistant is increasingly important to help users quickly f
arXiv:2602.02443v2 Announce Type: replace Abstract: Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that tra
arXiv:2605.00370v1 Announce Type: new Abstract: Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effe
arXiv:2605.00412v1 Announce Type: cross Abstract: World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement lea
arXiv:2604.26571v1 Announce Type: new Abstract: Municipal solid waste incineration is increasingly central to urban waste management, yet its sustainability benefit depends on controlling carbon emiss
arXiv:2604.25931v1 Announce Type: new Abstract: We identify a previously unknown calibration property of large language models: providing one confirmed intermediate fact toward a multi-step reasoning
arXiv:2604.25930v1 Announce Type: new Abstract: We study whether a structured recurrent state can serve as a compact associative backbone for language modeling while still supporting exact retrieval.
arXiv:2509.23980v2 Announce Type: replace Abstract: Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to V
arXiv:2604.26806v1 Announce Type: cross Abstract: Transformer-based architectures have established a dominant paradigm in global semantic perception; however, they remain fundamentally constrained by
arXiv:2604.25702v1 Announce Type: new Abstract: Contemporary neural machine translation (NMT) systems are almost exclusively built by training on supervised parallel data. Despite the tremendous progr
arXiv:2604.25300v1 Announce Type: new Abstract: Deploying tiny object perception on edge platforms is challenging because practical systems must satisfy both strict compute budgets and end-to-end late
arXiv:2603.01070v2 Announce Type: replace Abstract: Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logic
arXiv:2604.25296v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown transformative potential in medical applications, yet their performance is hindered by conventional
arXiv:2602.17697v2 Announce Type: replace Abstract: Large Language Models (LLMs) are being increasingly used across a wide range of tasks. However, their substantial computational demands raise concer
arXiv:2604.24938v1 Announce Type: cross Abstract: Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work has focused on importance criteria
arXiv:2604.25898v1 Announce Type: new Abstract: Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on prev
At Google Cloud Next ‘26, we announced that more than 50 Google-managed Model Context Protocol (MCP) servers are generally available or in preview, with more on the way. Why it matters: To move beyond
arXiv:2604.23468v1 Announce Type: cross Abstract: In 2016, Viazovska famously solved the sphere packing problem in dimension 8, using modular forms to construct a 'magic' function satisfying optimalit
arXiv:2604.24219v1 Announce Type: new Abstract: Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency, yet exist
arXiv:2603.21362v2 Announce Type: replace Abstract: LLM-as-Judge evaluation fails agent tasks because a fixed rubric cannot capture what matters for this task: code debugging demands Correctness and E
arXiv:2512.09972v5 Announce Type: replace-cross Abstract: Navigating the capability--efficiency trade-off in Large Language Models (LLMs) requires approximating a high-quality Pareto set. Existing mod
arXiv:2510.18346v2 Announce Type: replace Abstract: Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse ques
arXiv:2604.23399v1 Announce Type: new Abstract: High-performance semantic segmentation has achieved significant progress in recent years, often driven by increasingly large backbones and higher comput
arXiv:2604.23137v1 Announce Type: cross Abstract: Early detection and classifying brain tumors using Magnetic Resonance Imaging (MRI) images is highly important but difficult to extract in medical ima
arXiv:2604.22973v1 Announce Type: new Abstract: Predicting future trajectories of surrounding traffic agents is critical for safe autonomous navigation and collision avoidance. Despite all advances in
arXiv:2604.24361v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance in general machine translation, yet their ability in culture-aware scenarios remains poorl
arXiv:2604.24162v1 Announce Type: cross Abstract: Defending against backdoor attacks in large language models remains a critical practical challenge. Existing defenses mitigate these threats but typic
arXiv:2604.24609v1 Announce Type: new Abstract: Many sign language translation (SLT) systems operate on pose sequences instead of raw video to reduce input dimensionality, improve portability, and par
arXiv:2604.23862v1 Announce Type: cross Abstract: We investigate whether the Feed-Forward Network (FFN) sublayer in a decoder-only transformer can be replaced by an explicit learned memory graph while
arXiv:2604.23877v1 Announce Type: new Abstract: Logical reasoning serve as a central capability in LLMs and includes three main forms: deductive, inductive, and abductive reasoning. In this work, we s
arXiv:2604.24432v1 Announce Type: cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic unde
arXiv:2604.23970v1 Announce Type: new Abstract: Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-bu
arXiv:2604.23540v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable generative capabilities, yet accurately aligning complex textual prompts with synthesized layout
arXiv:2604.24348v1 Announce Type: new Abstract: The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS
arXiv:2604.23099v1 Announce Type: cross Abstract: Evaluating generative AI models is increasingly resource-intensive due to slow inference, expensive raters, and a rapidly growing landscape of models
arXiv:2604.22891v1 Announce Type: cross Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, qu
arXiv:2604.23150v1 Announce Type: cross Abstract: Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportion
arXiv:2603.26380v2 Announce Type: replace Abstract: The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales
arXiv:2604.22778v1 Announce Type: cross Abstract: We present the first systematic study of weight matrix singular value spectra during transformer pretraining, tracking full SVD decompositions of ever
arXiv:2502.03669v3 Announce Type: replace-cross Abstract: AI methods, such as generative models and reinforcement learning, have recently been applied to combinatorial optimization (CO) problems, espe
arXiv:2602.12134v2 Announce Type: replace Abstract: Existing work on value alignment typically characterizes value relations statically, ignoring how alignment interventions, such as prompting, fine-t
arXiv:2410.21548v3 Announce Type: replace Abstract: Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However
arXiv:2510.25977v4 Announce Type: replace Abstract: Emerging AI accelerators have started to gain attention and offer new opportunities for efficient inference of large language models (LLMs). Trainiu
arXiv:2511.07003v2 Announce Type: replace Abstract: Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust
arXiv:2604.22577v1 Announce Type: new Abstract: Autonomous agent systems such as OpenClaw introduce significant efficiency challenges due to long-context inputs and multi-turn reasoning. This results
arXiv:2604.22662v1 Announce Type: cross Abstract: Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little
arXiv:2601.12430v2 Announce Type: replace Abstract: Vision-language model (VLM) hallucination is commonly linked to imbalanced allocation of attention across input modalities: system, image and text.
arXiv:2604.21993v1 Announce Type: new Abstract: We study the detection of transient liquidity erosion ('crumbling quotes') in electronic limit order books, where observable quote deterioration may ref