Knowledge catalogue
arXiv:2610.21597v1 Announce Type: cross Abstract: Reverse engineering the data formats used by mobile software is skilled and slow, and using AI to assist with it is attractive. We evaluate this for t
arXiv:2610.21569v1 Announce Type: new Abstract: Diffusion models achieve strong performance in text-to-image generation, but they can still produce unsafe content. Training-free safety guidance offers
arXiv:2610.20615v1 Announce Type: new Abstract: Adaptive optimization workflows in machine learning, federated learning, quantum machine learning, and hybrid classical quantum systems often embed cont
arXiv:2601.10471v3 Announce Type: replace Abstract: We present DeFlow, a decoupled offline RL framework that leverages flow matching to faithfully capture complex behavior manifolds. Optimizing genera
arXiv:2610.21340v1 Announce Type: cross Abstract: Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space Theta subseteq R^D, causing relative entropy to
arXiv:2610.22356v1 Announce Type: new Abstract: Vision-language models still struggle to understand 3D spatial relations across views and update spatial judgments as the observer moves. A common appro
arXiv:2610.21251v1 Announce Type: new Abstract: Vision-language-action (VLA) models are expected to follow instructions like their language backbones, yet prior work has focused on What-level instruct
arXiv:2603.20804v2 Announce Type: replace Abstract: Vision-Language Navigation (VLN) systems are fundamentally constrained by partial observability, as an agent can only accumulate knowledge from loca
arXiv:2610.20652v1 Announce Type: new Abstract: Always-on virtual assistants increasingly personalize on-device to new user-specific commands via few-shot fine-tuning (e.g., LoRA), but this adaptation
arXiv:2610.22130v1 Announce Type: new Abstract: Key-value (KV) cache management has become a critical bottleneck for scaling Large Language Models (LLMs) to long-context scenarios due to linear memory
arXiv:2610.21123v1 Announce Type: cross Abstract: Series decomposition has emerged as a widely acknowledged paradigm in deep time series forecasting models. However, existing approaches predominantly
arXiv:2610.20795v1 Announce Type: new Abstract: Understanding why listeners enjoy music is difficult because the experience is subjective and changes as a piece unfolds. Electroencephalography (EEG) o
arXiv:2610.21644v1 Announce Type: cross Abstract: Pairwise Difference Learning for Classification (PDC) enhances supervised learning in low-data regimes by training a binary similarity classifier on p
arXiv:2610.22160v1 Announce Type: cross Abstract: Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate contro
arXiv:2610.21671v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves multimodal reasoning, but group-relative policy optimization broadcasts a single sequence
arXiv:2601.21138v3 Announce Type: replace Abstract: Record linkage, the process of matching records that refer to the same entity across datasets, is essential to empirical social science but remains
arXiv:2610.22186v1 Announce Type: cross Abstract: Recent advances in Omni Language Models (OLMs) provide a unified solution for audiovisual video captioning. Nevertheless, existing approaches predomin
arXiv:2610.20845v1 Announce Type: new Abstract: Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-impr
arXiv:2610.21018v1 Announce Type: new Abstract: When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from ex
arXiv:2504.00070v2 Announce Type: replace Abstract: This paper introduces Fuzzy Attention Network-Based Transformer (FANTF), an approach for time series forecasting, classification, and anomaly detect
arXiv:2610.22060v1 Announce Type: new Abstract: Discrete image generators learn the distribution of tokens produced by an image tokenizer. These token representations should be easy for generators to
arXiv:2610.20893v1 Announce Type: cross Abstract: Estimating causal effects on right-censored time-to-event outcomes is challenging under unmeasured confounding. Proximal causal inference addresses un
arXiv:2610.21937v1 Announce Type: new Abstract: Vision--language pre-training has enabled substantial progress in image--text retrieval and zero-shot recognition by learning transferable cross-modal r
arXiv:2610.21250v1 Announce Type: new Abstract: Multi-teacher on-policy distillation enables rectified-flow models with diffusion-transformer architectures to combine task-specific capabilities within
arXiv:2610.21165v1 Announce Type: new Abstract: Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window doe
arXiv:2610.21149v1 Announce Type: new Abstract: Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts. However, exis
arXiv:2610.21537v1 Announce Type: new Abstract: Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual learning
arXiv:2610.21779v1 Announce Type: new Abstract: Multi-modal semantic segmentation benefits from complementary sensors, but this benefit is fragile when some modalities are degraded or missing at test
arXiv:2610.21667v1 Announce Type: new Abstract: As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves as
arXiv:2610.20814v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy. Cor
arXiv:2610.21167v1 Announce Type: new Abstract: Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet multi-hop, long-horizon tasks remain challenging.
arXiv:2610.20662v1 Announce Type: cross Abstract: Graph Neural Additive Networks (GNANs) have emerged as effective, interpretable-by-design architectures for graph learning. They achieve transparency
arXiv:2610.22312v1 Announce Type: new Abstract: Spatial instructions describe how to move objects, transform regions, or modify their surroundings. When several operations are applied in sequence, eac
Guanzhi's deep dive thread: https://x.com/guanzhi_wang/status/2111127089428701366?s=46 ASPIRE is now open-source! Since our initial release, we've made exciting progress: 🤖 Real-world robot manipulati
arXiv:2610.21588v1 Announce Type: new Abstract: Audio-visual large language models (AV-LLMs) have made strong progress in multimodal understanding, yet most treat audio as monaural semantic content, l
arXiv:2610.21520v1 Announce Type: cross Abstract: Joint Acoustic Scene Classification (ASC) and Audio Tagging (AT) models traditionally rely on unconstrained multihead architectures. However, this des
arXiv:2610.21708v1 Announce Type: cross Abstract: When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a meas
arXiv:2610.22196v1 Announce Type: new Abstract: External-memory systems extend language-model applications beyond a context window, but their quality depends critically on the model executing the writ
arXiv:2610.21001v1 Announce Type: new Abstract: Column generation folklore warns that initial columns hurt: a warm start may bias the dual and slow the root of branch-price-and-cut. We show the opposi
arXiv:2610.20681v1 Announce Type: new Abstract: Formal inequality proving requires mathematical reasoning and exact computation, often connected through intermediate lemmas and goal reformulations. We
arXiv:2610.21995v1 Announce Type: new Abstract: Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant
arXiv:2606.09366v2 Announce Type: replace Abstract: Large language models (LLMs) provide a powerful reasoning backbone for speech understanding, but integrating continuous acoustic signals into a pret
arXiv:2610.21256v1 Announce Type: cross Abstract: Language models are often asked to make judgments: whether a proposed answer is correct, whether one statement follows logically from another, or whet
arXiv:2610.20617v1 Announce Type: cross Abstract: The committor function describes the probability that a stochastic dynamical system, while transitioning between two metastable states, will first rea
arXiv:2610.21411v1 Announce Type: new Abstract: Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require
arXiv:2610.20659v1 Announce Type: cross Abstract: Posterior inference for random fields from sparse observations presents two major challenges: accurately characterizing complex spatial uncertainty an
arXiv:2606.22305v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-
arXiv:2610.22080v1 Announce Type: new Abstract: A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training me
arXiv:2610.21881v1 Announce Type: new Abstract: Training language models for formal theorem proving requires large numbers of verifier calls. Slow checks and timeouts often leave GPUs waiting and with
arXiv:2610.21392v1 Announce Type: new Abstract: Reinforcement learning from internal feedback can improve language models without ground-truth answers or external verifiers. However, confidence and co
arXiv:2610.21783v1 Announce Type: new Abstract: We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D re
arXiv:2610.21030v1 Announce Type: cross Abstract: Reasoning-conditioned embeddings can improve retrieval by progressively refining semantic constraints. However, additional reasoning may introduce ove
In October 2026 Georgi Gerganov posted that he ran **llama.cpp v0.7.0 on a 128‑GB‑RAM Mac (Spark)**, serving the Qwen3.8‑Flash‑Next GGUF model in IQ4_NL precision. The command used was `llama serve -h
arXiv:2610.20939v1 Announce Type: new Abstract: Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to G
arXiv:2610.21607v1 Announce Type: new Abstract: Despite their practical significance, modern AI systems pose significant societal risks, including toxicity, malicious use, and misinformation. Their mi
arXiv:2406.07243v4 Announce Type: replace Abstract: Generative large language models (LLMs) have been shown to exhibit harmful biases and stereotypes. While safety fine-tuning typically takes place in
arXiv:2610.21007v1 Announce Type: new Abstract: Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocation
arXiv:2602.08901v2 Announce Type: replace Abstract: Large language models (LLMs) can memorize and reproduce training sequences verbatim, raising privacy and copyright concerns. Existing mitigation met
arXiv:2610.22276v1 Announce Type: new Abstract: Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial re
arXiv:2610.22177v1 Announce Type: cross Abstract: Feed-forward transformer models have recently achieved strong performance in multi-view 3D reconstruction, but they still rely primarily on appearance