Knowledge catalogue
arXiv:2610.07376v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate in interactive environments, where they need to make sequential decisions through observation, ac
arXiv:2610.08586v1 Announce Type: new Abstract: Long conversational agents have become essential in our daily lives. They must remember what was said long back in order to help us efficiently complete
OCR is the perfect example of a use case that has been dominated by legacy/brittle systems, and can be solved both accurately and cheaply by applying the right amount of agentic intelligence. A proper
arXiv:2610.07782v1 Announce Type: new Abstract: Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache
arXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-qu
arXiv:2610.08675v1 Announce Type: new Abstract: Financial reports repeat values across periods, metrics and accounting lines, allowing an LLM-generated calculation to be numerically correct while citi
arXiv:2512.23065v4 Announce Type: replace Abstract: The introduction of BERT established encoder-only transformer models as a foundational paradigm in natural language processing. Encoder-only models
arXiv:2610.08358v1 Announce Type: cross Abstract: Post-training quantization is a standard route to fitting vision transformers (ViTs) into edge compute and memory budgets, yet quantized models become
arXiv:2610.07895v1 Announce Type: new Abstract: Sea surface temperature (SST) forecasting depends on local temporal persistence, regional spatial dependence, and environmental conditions that evolve w
arXiv:2610.07803v1 Announce Type: new Abstract: Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they of
arXiv:2610.07570v1 Announce Type: new Abstract: In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism o
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language mode
arXiv:2610.07334v1 Announce Type: new Abstract: Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring kno
We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device
arXiv:2610.05269v1 Announce Type: new Abstract: We develop a Unified Scaling Law and a Unified Theory of Time Series Learning to understand how model capacity and historical information support foreca
For modern AI and RAG applications, achieving high search relevance requires that you combine at least two techniques: vector search for semantic context, and full-text search (FTS) for keyword precis
arXiv:2610.05303v1 Announce Type: new Abstract: A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed
arXiv:2610.05765v1 Announce Type: new Abstract: Goal-conditioned imitation learning (GCIL) with flow matching is a promising framework that can represent multimodal behaviors while adapting to diverse
Add a voice travel concierge to an airline app with Amazon Bedrock AgentCore, Amazon Nova Sonic for real-time speech, and Amazon Bedrock Knowledge Bases for policy answers. Travelers change seats, che
arXiv:2603.11048v2 Announce Type: replace Abstract: We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting from charact
arXiv:2610.05559v1 Announce Type: new Abstract: Industrial sequential recommender systems operate over massive item catalogs (e.g., 10^5--10^7 items). Multi-label recommendation models are trained wit
arXiv:2606.16184v2 Announce Type: replace Abstract: Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. Existing methods encod
https://huggingface.co/google/embeddinggemma-2 EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combina
arXiv:2610.04129v1 Announce Type: cross Abstract: We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summ
arXiv:2610.06588v1 Announce Type: new Abstract: Long-horizon camera-controlled video generation relies on persistent memory to maintain scene consistency. Existing systems follow two strategies to ach
arXiv:2610.05024v1 Announce Type: new Abstract: Aerial vision-and-language navigation (VLN) enables unmanned aerial vehicles to execute long-horizon natural-language instructions from visual observati
arXiv:2610.05023v1 Announce Type: new Abstract: We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image r
arXiv:2610.06801v1 Announce Type: new Abstract: Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resol
arXiv:2607.09082v2 Announce Type: replace Abstract: Training-free in-context segmentation enables new object categories to be introduced at inference time from a single annotated reference image, elim
arXiv:2606.16496v2 Announce Type: replace-cross Abstract: Large multimodal language models (MLLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic poli
arXiv:2610.05097v1 Announce Type: new Abstract: As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memo
arXiv:2610.05940v1 Announce Type: new Abstract: Despite their impressive performance on a wide range of video understanding tasks, current Vision Language Models (VLMs) are predominantly designed for
arXiv:2610.04893v1 Announce Type: new Abstract: Industrial Internet of Things (IIoT) systems generate high-dimensional sensor telemetry from interconnected components, where faults can propagate acros
arXiv:2610.03799v1 Announce Type: new Abstract: Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discret
arXiv:2610.05350v1 Announce Type: new Abstract: Behavioral Foundation Models (BFMs) aim to solve a wide range of downstream tasks without test-time policy learning by inferring a task vector from the
arXiv:2610.03984v1 Announce Type: cross Abstract: Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time comput
arXiv:2610.05932v1 Announce Type: new Abstract: Visual voice cloning requires intelligible, speaker-consistent speech synchronized with visible articulation. However, sequential multimodal conditionin
arXiv:2610.06616v1 Announce Type: new Abstract: The design of a video encoder determines when frames begin to interact and which frame-specific visual evidence remains accessible to the language model
arXiv:2610.05700v1 Announce Type: new Abstract: Recurrent sequence models must decide how strongly to overwrite their memory at each token. Read as Bayesian filtering, this write is the gain of a Kalm
arXiv:2610.02451v1 Announce Type: new Abstract: Effective wildfire monitoring requires relating visual evidence to physical fire dynamics, yet real videos with synchronized physical annotations are sc
arXiv:2610.03413v1 Announce Type: new Abstract: Sequential learning systems often make decisions from accumulated experience while receiving high-dimensional inputs whose distribution may change over
arXiv:2610.03531v1 Announce Type: new Abstract: Authorship Attribution (AA) requires capturing fine-grained stylistic characteristics, making it particularly challenging in zero-shot (ZS) settings whe
arXiv:2406.19892v5 Announce Type: replace Abstract: This article presents multilingual deep learning models for identifying web registers -- text varieties such as news reports and discussion forums -
arXiv:2610.03387v1 Announce Type: new Abstract: Typed decision models return choices or distributions over answer options supplied at request time. Accuracy with complete options does not establish wh
arXiv:2610.02376v1 Announce Type: cross Abstract: Co-designing ML models and the accelerators that run them is an unusual reasoning task: architects must draw confident, high-stakes conclusions about
arXiv:2610.02292v1 Announce Type: cross Abstract: Human activity recognition (HAR) is increasingly important for healthcare, well-being, and daily monitoring ap- plications, for which detecting alimen
arXiv:2610.03524v1 Announce Type: new Abstract: General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and col
arXiv:2610.03296v1 Announce Type: new Abstract: Complex reasoning queries can be decomposed into directed acyclic task graphs and distributed across heterogeneous LLMs, reducing latency through parall
arXiv:2610.03198v1 Announce Type: new Abstract: The memory footprint of the key-value (KV) cache constrains the practical use of long-context models, and it dominates cost when one prefilled context m
arXiv:2610.02525v1 Announce Type: new Abstract: Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because suc
arXiv:2610.03056v1 Announce Type: new Abstract: Large language models are increasingly used as reasoning components in AI-driven materials Co-Scientists, yet the reliability of the resulting verificat
arXiv:2606.18717v2 Announce Type: replace-cross Abstract: Turkish is agglutinative: meaning is carried by morphemes, yet the subword tokenizers that drive modern language models split words by corpus
arXiv:2610.03494v1 Announce Type: new Abstract: Long-term forecasting models commonly process all patches in a look-back window using the same fixed stack. Older contextual patches and recent evidence
arXiv:2610.03135v1 Announce Type: new Abstract: Serving long-context autoregressive language models is constrained by the key-value (KV) cache. Most dynamic eviction methods score token importance per
arXiv:2610.02953v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compress
arXiv:2610.03029v1 Announce Type: new Abstract: Gene set analysis is a cornerstone of functional genomics, yet it remains labor-intensive and heavily dependent on manual curation and expert biological
arXiv:2610.02779v1 Announce Type: new Abstract: In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video gener
arXiv:2610.02769v1 Announce Type: cross Abstract: Language agents should draw on prior attempts and environmental feedback to improve subsequent decisions within the same task. However, providing addi
LFM2.5-Encoder-350M is a multilingual bidirectional encoder built on the LFM2 architecture — a larger encoder for maximum downstream quality. It is a masked language model with full bidirectional atte
arXiv:2610.00969v1 Announce Type: cross Abstract: Large language models (LLMs) have been increasingly used for financial document analysis, including earnings call transcripts (ECTs). Beyond generatin