Knowledge catalogue
arXiv:2602.07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidi
arXiv:2509.13805v4 Announce Type: replace-cross Abstract: Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-train
arXiv:2606.00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moder
We wrapped a live session on M3 yesterday with the @togethercompute team & our researchers @zpysky1125 and @HaohaiSun A few highlights 🧵 1. MSA (MiniMax Sparse Attention) is the star ⭐️. Unlike CSA/HC
arXiv:2606.00046v1 Announce Type: cross Abstract: Video platforms such as YouTube have reshaped how users engage with entertainment and information, emphasizing brief, highly engaging content such as
arXiv:2606.02106v1 Announce Type: new Abstract: We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-co
6 months ago I said I won't stop until I have Kimi at home, after 10+ botched REAPs I finally have it Needs benchmarking of course. - 45 tok/s decode - 954 tok/s prefill no cache - 95k+ tok/s cached p
activegraph longmemeval experiment #1: https://x.com/ActiveGraphAI/status/2059106393433780292?s=20 [technical blog post] “Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S” ——
arXiv:2605.31522v1 Announce Type: new Abstract: Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecul
arXiv:2605.31065v1 Announce Type: cross Abstract: Non-terrestrial networks (NTNs) are expected to play a pivotal role in sixth-generation (6G) systems by enabling ubiquitous connectivity and massive c
arXiv:2605.30947v1 Announce Type: new Abstract: LLM-based research agents have advanced rapidly in science and engineering, where research is organized around executable experiments, code, and quantit
arXiv:2605.30884v1 Announce Type: new Abstract: Existing agentic reinforcement learning methods for GUI grounding have limitations at two levels. At the data level, current approaches typically treat
arXiv:2605.30965v1 Announce Type: cross Abstract: Recent advancements in text-guided audio generation have yielded promising results in diverse domains, including sound effects, speech, and music. How
arXiv:2605.30615v1 Announce Type: new Abstract: In selective classification, a model predicts the labels of data samples where it is confident, and abstains from predicting labels for samples on which
arXiv:2605.31201v1 Announce Type: new Abstract: Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source
arXiv:2603.22744v2 Announce Type: replace Abstract: Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct
arXiv:2605.31421v1 Announce Type: cross Abstract: In this paper, we show the possibility of a direct injection of algorithms into neural network architecture. We focus on a complex algorithm, that is,
arXiv:2512.02743v2 Announce Type: replace-cross Abstract: Hate speech in online videos is posing an increasingly serious threat to digital platforms, especially as video content becomes increasingly m
arXiv:2605.25193v2 Announce Type: replace Abstract: Visual and acoustic events in the physical world are inherently coupled, yet existing video editing methods typically adopt decoupled pipelines, lac
arXiv:2605.31593v1 Announce Type: cross Abstract: Language models can find thousands of severe software vulnerabilities, and agents are increasingly being misused for cyberattacks. To avoid detection,
arXiv:2605.30694v1 Announce Type: new Abstract: Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local
arXiv:2605.31457v1 Announce Type: new Abstract: With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing me
arXiv:2605.30481v1 Announce Type: new Abstract: Large language models (LLMs) are widely used as cross-lingual knowledge interfaces. However, culturally grounded questions often reflect globally domina
This recent @latentspacepod pod was a good one (they usually all are). One specific piece resonated: They were talking about AI agents writing code, and the line was basically that without caution / d
arXiv:2605.29454v1 Announce Type: new Abstract: While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing
arXiv:2605.30070v1 Announce Type: cross Abstract: Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPS
arXiv:2605.29458v1 Announce Type: cross Abstract: Accurately simulating the decisions of a specific individual remains challenging for large language models (LLMs), partly because persona information
arXiv:2605.28914v1 Announce Type: cross Abstract: Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model C
arXiv:2605.29225v1 Announce Type: new Abstract: Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, lea
arXiv:2605.30214v1 Announce Type: new Abstract: Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about referenc
arXiv:2605.28828v1 Announce Type: cross Abstract: Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation wh
arXiv:2605.29146v1 Announce Type: cross Abstract: Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional
arXiv:2605.29324v1 Announce Type: new Abstract: Mobile GUI agents excel at immediate reactive control but frequently fail in realistic, long-horizon tasks that require memory. This failure stems from
arXiv:2605.30289v1 Announce Type: new Abstract: Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric
arXiv:2601.11178v2 Announce Type: replace Abstract: Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interp
arXiv:2605.30060v1 Announce Type: new Abstract: This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built
arXiv:2509.24895v2 Announce Type: replace Abstract: While protein language models (PLMs) are one of the most promising avenues of research for future de novo protein design, the way in which they tran
arXiv:2601.10714v2 Announce Type: replace Abstract: We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, materia
arXiv:2512.01970v3 Announce Type: replace Abstract: Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Comple
arXiv:2605.27988v1 Announce Type: new Abstract: Bias evaluation for language models has made substantial progress on bounded comparisons, such as overt derogation, stereotype association, or label-sen
arXiv:2605.28456v1 Announce Type: new Abstract: Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually
arXiv:2603.02702v3 Announce Type: replace Abstract: The financial domain involves a variety of important time-series problems. Recently, time-series analysis methods that jointly leverage textual and
arXiv:2604.05333v3 Announce Type: replace Abstract: Modern LLM agents increasingly rely on reusable skills, and as they interact with personal applications, web browsers, and other interfaces, skill l
arXiv:2605.28643v1 Announce Type: new Abstract: Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another cru
arXiv:2605.27703v1 Announce Type: new Abstract: Large Language Models are increasingly deployed inside agentic systems, where they must follow structured protocols, adapt to evolving states, and opera
arXiv:2510.06928v2 Announce Type: replace Abstract: Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of vis
arXiv:2605.28320v1 Announce Type: cross Abstract: This paper addresses the problem of identifying parsimonious explicit piece-wise polynomial relationships that might involve a relatively large number
arXiv:2605.27853v1 Announce Type: new Abstract: We present MolLingo, a multi-agent system that emulates the reasoning process of a chemist to automate molecular design. Existing LLM-based approaches e
Organizations are unlocking entirely new ways to use image generation and editing across their industries. To drive next-generation experiences, businesses are embedding AI directly into creative, age
arXiv:2605.28201v1 Announce Type: new Abstract: Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into ext
arXiv:2602.22787v2 Announce Type: replace-cross Abstract: Large language model (LLM) hallucinations, meaning fluent but factually incorrect generations, fall into two types: faithfulness violations, w
arXiv:2605.28231v1 Announce Type: cross Abstract: We present ProgVLA, a compact vision-language-action (VLA) model designed for reliable robot manipulation under tight compute and memory budgets. The
arXiv:2605.28100v1 Announce Type: cross Abstract: In an era where climate change aggravates environmental uncertainties, the identification and detection of event precursors are becoming crucial to mi
arXiv:2605.27959v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based appro
arXiv:2605.28741v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) are rapidly evolving toward true multimodal reasoning, with visual search representing a concrete instantiation of
arXiv:2605.28219v1 Announce Type: cross Abstract: Unsupervised learning methods -- topic modeling, partition-based and density-based clustering -- produce data groupings without human guidance, yet ch
arXiv:2605.27539v1 Announce Type: new Abstract: Many children experience challenges in emotional regulation and social interaction, which can limit their participation in everyday activities and thera
arXiv:2605.28000v1 Announce Type: cross Abstract: Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting
arXiv:2605.28187v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as scholar recommenders, shaping who is seen as an expert in academia. Existing audits remain Engli
arXiv:2605.27174v1 Announce Type: cross Abstract: Artificial intelligence is increasingly being integrated into professional audio production workflows, yet a gap persists between the tools developers