Knowledge catalogue
arXiv:2608.25826v1 Announce Type: new Abstract: A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web
arXiv:2608.24982v1 Announce Type: new Abstract: Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-T
arXiv:2608.26105v1 Announce Type: new Abstract: Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be u
arXiv:2608.26013v1 Announce Type: new Abstract: Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typic
arXiv:2608.25302v1 Announce Type: new Abstract: Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias. T
arXiv:2511.09790v2 Announce Type: replace-cross Abstract: Dynamical system (DS)-based learning from demonstration (LfD) is a powerful tool for generating motion plans in the operation ('task') space o
arXiv:2608.24127v1 Announce Type: cross Abstract: Telephone fraud is pervasive and costly, but its inner workings are rarely observed at scale. We analyze a complete corpus of 10,211 inbound scam and
arXiv:2608.23653v1 Announce Type: cross Abstract: AI agents are increasingly used for simulation-driven engineering. Physical system modeling presents different requirements from general-purpose code
arXiv:2608.24303v1 Announce Type: new Abstract: Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to
arXiv:2608.24369v1 Announce Type: new Abstract: While large language models (LLMs) possess vast zero-shot procedural knowledge, their tendency to produce homogenized logic often obscures the unique, i
arXiv:2608.23924v1 Announce Type: cross Abstract: Repetitive maritime operations can be effectively learned using the Imitation Learning (IL) paradigm, which transfers human expertise directly to Unma
arXiv:2608.24134v1 Announce Type: new Abstract: The majority of our everyday activities are procedural and consist of sequences of interdependent steps. However, existing benchmarks for Visual Agents
arXiv:2607.08960v2 Announce Type: replace-cross Abstract: Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be exec
arXiv:2608.24541v1 Announce Type: new Abstract: Surgical instrument segmentation (SIS) is fundamental for computer-assisted surgery, where reliable instrument masks enable precise scene understanding
arXiv:2608.24273v1 Announce Type: new Abstract: Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forget
arXiv:2608.23982v1 Announce Type: new Abstract: Scientific reasoning requires language models to retrieve specialized knowledge and incorporate it reliably into multi-step computation. Conditional mem
arXiv:2608.24026v1 Announce Type: new Abstract: Recent end-to-end neural motion planners generate trajectories from raw sensor observations, avoiding the privileged geometric models required by classi
Deborah Mary Sophia / Reuters: Nvidia forecasts Q3 revenue of 108B, above a 104B estimate, and expects FY 2028 revenue to grow by about 70%; NVDA jumps 4%+ after hours — Nvidia's (NVDA.O) quarterly re
Presented by Tata Communications Enterprises are deploying AI agents, voice AI, and automation across messaging, voice, and digital channels faster than the architecture meant to support it. Most of t
arXiv:2608.24428v1 Announce Type: cross Abstract: Using monthly Nino-3.4 anomalies through July 2026, we investigate how much predictive information is contained in delayed observations of the index.
arXiv:2608.23568v1 Announce Type: new Abstract: Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a mem
arXiv:2608.24291v1 Announce Type: new Abstract: Paper-to-code reproduction asks scientific AI agents to turn research papers into executable repositories that preserve the paper's method, protocol and
arXiv:2601.17027v2 Announce Type: replace-cross Abstract: While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by t
arXiv:2608.24870v1 Announce Type: new Abstract: Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and variable tool-use trajectories. Single
arXiv:2608.23952v1 Announce Type: cross Abstract: Federated video anomaly detection trains model collaboratively without sharing raw surveillance footage, but limited server-side visibility lets compr
arXiv:2608.23953v1 Announce Type: cross Abstract: An agent harness is what turns a language model into an autonomous agent: the surrounding code that builds the model's context, mediates its tools, ru
arXiv:2608.22910v1 Announce Type: cross Abstract: We develop a finite-width geometric framework describing how learned feature geometries are organized, transported, and selectively aligned in deep ne
arXiv:2403.04931v4 Announce Type: replace Abstract: As the capabilities of artificial intelligence (AI) continue to expand rapidly, Human-AI (HAI) Collaboration, combining human intellect and AI syste
arXiv:2608.21377v1 Announce Type: cross Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied pr
arXiv:2608.22478v1 Announce Type: cross Abstract: Implied volatility surfaces summarise the option market and are central to many financial applications. Forecasting their future evolution requires mo
arXiv:2608.21919v1 Announce Type: new Abstract: Recent work has proposed that reasoning and memorization in language models can be characterized by a single representation direction, including methods
arXiv:2608.22577v1 Announce Type: new Abstract: Long-horizon GUI agents can retain a complete interaction trace cheaply as textual action records, but expose only a few past events to the policy in hi
arXiv:2608.21860v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has significantly enhanced the multi-step problem-solving capabilities of large language models (LLMs) by introducing
arXiv:2608.21690v1 Announce Type: new Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier in
arXiv:2608.21438v1 Announce Type: new Abstract: Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments, but remains difficult because natural language de
arXiv:2608.21946v1 Announce Type: cross Abstract: Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable expl
arXiv:2606.17642v3 Announce Type: replace Abstract: Financial multimodal reasoning requires agents to coordinate numerical computation, retrieval, visual interpretation, and temporal grounding across
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while reta
arXiv:2608.22224v1 Announce Type: cross Abstract: Temporal Domain Generalization (TDG) aims to learn from historical domains and generalize to unseen future distributions under concept drift. Neverthe
arXiv:2608.22310v1 Announce Type: new Abstract: Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite d
Impressive work from Alibaba. (bookmark it) If you build long-running agents and keep rewriting your memory schema, take a look at this approach. It basically treats agent context management as a prog
arXiv:2606.14782v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with lon
arXiv:2608.22648v1 Announce Type: cross Abstract: As an increasing number of critical applications, including environmental, emergency, meteorological, and agricultural, rely on real-time anomaly dete
arXiv:2608.22061v1 Announce Type: new Abstract: Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and the
arXiv:2608.21386v1 Announce Type: cross Abstract: Given a task described by a few examples, how should a model be specialized to it? Four mechanisms are available -- zero-shot, in-context attention, t
arXiv:2608.23323v1 Announce Type: cross Abstract: Continuous optimisation methods need to balance sharing information and maintaining alternative search directions. In this paper, we introduce Mycelia
arXiv:2608.22643v1 Announce Type: cross Abstract: Deploying large language models on edge devices is increasingly limited by a widening gap between model size and available memory. Existing approaches
arXiv:2608.23552v1 Announce Type: new Abstract: Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context
arXiv:2608.23463v1 Announce Type: new Abstract: The quadratic growth of attention computation and key-value (KV) cache with respect to sequence length is a central bottleneck for ultra-long-context la
arXiv:2608.22118v1 Announce Type: new Abstract: LLM responses are based on the internet (via training or RAG), and AI is now used to generate a significant amount of content online (Paredes et al., 20
arXiv:2608.22354v1 Announce Type: cross Abstract: Delta-Rule recurrent models maintain a fixed-size state, enabling O(1) inference memory but potentially becoming unstable under extreme-context extrap
arXiv:2608.21466v1 Announce Type: cross Abstract: We develop spectral algorithms for selecting state-space partitions that define averaging kernels for finite, ergodic and reversible Markov chains. Fo
arXiv:2608.21952v1 Announce Type: new Abstract: Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providin
arXiv:2608.23034v1 Announce Type: cross Abstract: Controlling restricted knowledge in large language models is essential for model alignment and safe deployment. Test-time unlearning avoids costly ret
arXiv:2608.21898v1 Announce Type: new Abstract: Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding
arXiv:2608.23020v1 Announce Type: cross Abstract: Large language models (LLMs) require effective unlearning to address privacy regulations and safety concerns. However, achieving precise forgetting wi
arXiv:2608.22521v1 Announce Type: new Abstract: Visual autoregressive (VAR) models have emerged as a fast, high-quality alternative to diffusion for text-to-image generation, but like diffusion models
arXiv:2608.21244v1 Announce Type: new Abstract: Vision-language models enable training-free video anomaly detection by answering questions about video segments. VAD benchmarks, however, require a scal
arXiv:2608.21243v1 Announce Type: cross Abstract: Sequential recommendation predicts the next item from a user's interaction history, but not every interaction is equally informative. Real logs combin
arXiv:2608.20634v1 Announce Type: cross Abstract: Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around