Knowledge catalogue
arXiv:2605.10120v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as micr
arXiv:2605.10379v1 Announce Type: new Abstract: Large language models (LLMs) have become capable mathematical problem-solvers, often producing correct proofs for challenging problems. However, correct
arXiv:2605.09235v1 Announce Type: cross Abstract: One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillatio
arXiv:2505.23617v3 Announce Type: replace-cross Abstract: Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time p
arXiv:2605.08646v1 Announce Type: cross Abstract: Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preser
arXiv:2507.23009v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved remarkable results on a range of standardized tests originally designed to assess human cognitive a
arXiv:2605.08786v1 Announce Type: new Abstract: Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge
arXiv:2605.10614v1 Announce Type: new Abstract: Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear
arXiv:2605.08454v1 Announce Type: cross Abstract: Recovering continuous-time dynamics from discrete observations is difficult because local supervision (e.g., pointwise regression targets, derivative
arXiv:2605.10357v1 Announce Type: cross Abstract: Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce ex
arXiv:2605.09906v1 Announce Type: new Abstract: Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cros
arXiv:2605.10298v1 Announce Type: new Abstract: Accurate next-day active fire forecasts can support early warning, disaster response, forest risk assessment, and downstream estimation of fire-related
arXiv:2605.09598v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently shown strong potential in soccer video understanding. However, given the high complexity of soccer videos du
arXiv:2605.08583v1 Announce Type: new Abstract: Large language models are increasingly used in scientific writing, yet they can fabricate citation-shaped references that appear plausible but fail bibl
arXiv:2602.03916v3 Announce Type: replace-cross Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs).
arXiv:2505.11604v5 Announce Type: replace Abstract: Editing presentation slides is a frequent yet tedious task, ranging from creative layout design to repetitive text maintenance. While recent GUI-bas
arXiv:2605.09929v1 Announce Type: new Abstract: Deploying large language models in telecommunications requires more than task accuracy. In realistic workflows, a model may inherit partially completed
arXiv:2605.09844v1 Announce Type: new Abstract: The Metacognitive Probe is an exploratory five-task, 15-slot diagnostic that decomposes an LLM's confidence behaviour into five behaviourally-distinct d
arXiv:2605.09330v1 Announce Type: cross Abstract: Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulner
arXiv:2601.02954v3 Announce Type: replace-cross Abstract: Large audio-language models have made rapid progress in recognizing what is present in an audio clip, but spatial audio-language understanding
arXiv:2605.09544v1 Announce Type: new Abstract: Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution ca
arXiv:2603.08588v2 Announce Type: replace-cross Abstract: State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computat
arXiv:2602.17283v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on f
arXiv:2605.08974v1 Announce Type: cross Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We arg
arXiv:2601.22478v3 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models
arXiv:2605.08168v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising path to generalist robot control, but their inference latency causes observation staleness when
arXiv:2511.12878v4 Announce Type: replace Abstract: Forecasting how human hands move in egocentric views is critical for applications like augmented reality and human-robot policy transfer. Recently,
arXiv:2605.05831v2 Announce Type: replace Abstract: The communication of scientific knowledge has become increasingly multimodal, spanning text, visuals, and speech through materials such as research
arXiv:2605.09920v1 Announce Type: cross Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising post-training paradigm for Large Language Models (LLMs
arXiv:2605.10106v1 Announce Type: cross Abstract: Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training
arXiv:2605.09109v1 Announce Type: new Abstract: Many continuous-control problems ship with a competent but suboptimal controller (a tuned PID, a hand-designed gait). A growing family of methods uses s
arXiv:2605.09360v1 Announce Type: cross Abstract: Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this pro
arXiv:2605.07066v1 Announce Type: new Abstract: Autonomous systems that build structures from natural-language instructions need reliable spatial reasoning, yet large language models (LLMs) make syste
arXiv:2605.06924v1 Announce Type: cross Abstract: Synthesizing consistent and coherent long video remains a fundamental challenge. Existing methods suffer from semantic drift and narrative collapse ov
arXiv:2603.04676v2 Announce Type: replace-cross Abstract: Multi-image reasoning remains a significant challenge for vision-language models (VLMs). We investigate a previously overlooked phenomenon: du
arXiv:2605.06997v1 Announce Type: new Abstract: Long chain-of-thought reasoning and agentic tool-calling produce traces spanning tens of thousands of tokens, yet Transformer KV caches grow linearly wi
arXiv:2605.06669v1 Announce Type: cross Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies.
arXiv:2512.12602v4 Announce Type: replace Abstract: In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rul
arXiv:2605.06982v1 Announce Type: new Abstract: Embedding models in natural language processing (NLP) increasingly rely on deep architectures such as BERT, while simpler models such as Word2Vec provid
arXiv:2605.07861v1 Announce Type: new Abstract: Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods form
arXiv:2605.08083v1 Announce Type: new Abstract: Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during infe
// LLMs Improving LLMs // Interesting progress the past of couple of weeks around self-improving AI agents. If autoresearch was interesting, you will like this read. (bookmark it) We've been hand-tuni
arXiv:2603.09652v3 Announce Type: replace Abstract: With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynami
arXiv:2605.07792v1 Announce Type: cross Abstract: Neural operators (NOs) are designed to learn maps between infinite-dimensional function spaces. We propose a novel reframing of their use. By introduc
arXiv:2605.06728v1 Announce Type: cross Abstract: Interpreting transcriptomic data is one of the most common analytical tasks in modern biology. Yet most current models either consume expression profi
arXiv:2605.07141v1 Announce Type: cross Abstract: Open-world referring segmentation requires grounding unconstrained language expressions to precise pixel-level regions. Existing multimodal large lang
arXiv:2605.07477v1 Announce Type: new Abstract: Recent text-guided image editing (TIE) models have achieved remarkable progress, however, many edited results still suffer from artifacts, unintended mo
arXiv:2605.08000v1 Announce Type: new Abstract: Recent progress in dense optical flow has been driven by increasingly complex architectures and multi-step refinement for test-time scaling. While these
arXiv:2605.07630v1 Announce Type: cross Abstract: When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may b
arXiv:2605.07823v1 Announce Type: new Abstract: Online group chats are social spaces with implicit behavior patterns that, when broken, are often met with social sanctioning from the group. The abilit
arXiv:2605.07288v1 Announce Type: cross Abstract: The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned W
arXiv:2605.06931v1 Announce Type: new Abstract: Learning-based approaches to NP-hard problems have shown increasing promise, but their progress is fundamentally constrained by the high cost of generat
arXiv:2605.07073v1 Announce Type: new Abstract: Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls.
arXiv:2605.07807v1 Announce Type: cross Abstract: Text-to-CAD has recently emerged as an important task with the potential to substantially accelerate design workflows. Despite its significance, there
arXiv:2512.03454v4 Announce Type: replace-cross Abstract: Interpreting natural-language commands to localize target objects is critical for autonomous driving (AD). Existing visual grounding (VG) meth
arXiv:2605.06765v1 Announce Type: cross Abstract: Human speech conveys expressiveness beyond linguistic content, including personality, mood, or performance elements, such as a comforting tone or humm
arXiv:2605.07114v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a central paradigm for improving the reasoning capabilities of large language model
arXiv:2605.04076v1 Announce Type: new Abstract: U.S. financial institutions deploying AI-based fraud detection face a fragmented compliance landscape spanning four regulatory frameworks -- OCC Bulleti
arXiv:2601.20634v2 Announce Type: replace Abstract: Virtual sensors replace expensive physical sensors in critical applications through machine learning by predicting target signals from available mea
arXiv:2605.05014v1 Announce Type: new Abstract: Autonomous driving must operate across diverse surfaces to enable safe mobility. However, most driving datasets are captured on well-paved flat roads. M