Knowledge catalogue
arXiv:2512.21094v2 Announce Type: replace Abstract: Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet it
arXiv:2606.02624v1 Announce Type: cross Abstract: AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather
arXiv:2509.09685v5 Announce Type: replace-cross Abstract: We present TalkPlayData 2, a synthetic dataset for multimodal conversational music recommendation generated by an agentic data pipeline. In th
arXiv:2606.03606v1 Announce Type: cross Abstract: Large language models achieve strong performance on arithmetic reasoning benchmarks, and one common response to arithmetic brittleness is to delegate
arXiv:2606.03806v1 Announce Type: new Abstract: Temperature-emissivity-texture (TeX) decomposition seeks to recover object heat state, material spectral response, and visible-like geometric texture fr
arXiv:2606.03686v1 Announce Type: new Abstract: We present DeepSpeak-Agentic, a dataset of videos comprising over 37 hours of semi-structured conversations between a human and an embodied AI agent. We
arXiv:2606.03043v1 Announce Type: new Abstract: LMs-as-judges are now standard, yet judges agree strongly with one another while agreeing only weakly with humans. We test whether this reflects shared
arXiv:2606.03907v1 Announce Type: cross Abstract: Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from s
arXiv:2606.03305v1 Announce Type: new Abstract: Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for de
arXiv:2606.02646v1 Announce Type: cross Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-paramete
arXiv:2606.03250v1 Announce Type: new Abstract: Digital healthcare generates vast amounts of clinical text that can support AI-assisted applications, yet German biomedical language models remain limit
This is really intellectually dishonest. I have not been arguing that LLM token prices are increasing (though the all you can eat buffet is over), I have been arguing the *opposite*, viz that they wil
This story was so implausible that the only way it even (kind of) made sense if it is some sort of internal accounting placeholder at a cloud provider using their own compute. And even then it seems u
thought I was supposed to be the shit-posting account here shower thought If: 1. AI is smarter than humans at law, therapy, etc. 2. Humans still like talking to other humans. Then: Humans are just an
arXiv:2606.03503v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (Co
Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a
arXiv:2606.03462v1 Announce Type: new Abstract: Graph neural networks have achieved strong performance on graph-structured data, but their effectiveness depends heavily on the quality of the observed
arXiv:2606.03401v1 Announce Type: new Abstract: Scientific images function as critical evidence in research communication, yet their integrity faces unprecedented threats from AI-generated content tha
arXiv:2510.23469v2 Announce Type: replace Abstract: Self-supervised pre-training on unlabeled graph data has become a common paradigm for Graph Neural Networks (GNNs). However, an objective gap often
arXiv:2606.03800v1 Announce Type: cross Abstract: The supply of high-quality training tasks is a central bottleneck for reinforcement learning from verifiable rewards (RLVR) on agentic language models
arXiv:2606.03036v1 Announce Type: new Abstract: LLMs have evolved from basic chatbots to the backbone of the AI ecosystem, now widely used in healthcare, schools, and government services. The domain-w
arXiv:2606.03629v1 Announce Type: new Abstract: Assessing the quality of time series (TS) data is fundamental yet inherently challenging due to the multifaceted nature of quality dimensions. Recently,
arXiv:2606.03626v1 Announce Type: cross Abstract: Vision-language models (VLMs) have been explored for visual programming, where they generate code to solve visual tasks. However, most prior work focu
Uber Caps Usage of AI Tools Like Claude Code to Manage Costs I wrote the other day about Uber blowing its 2026 AI budget in four months, and how that wasn't particularly surprising given they would ha
Using open models and inference clouds (which serve open models) is a leading indicator of what is to come. The advantage of open weights is that you can train, serve, and continually improve your own
Ollama v0.30.4 is a patch release addressing a bug in the llama-server component related to incorrect parameter wiring in the Gemma 4 model implementation. This fix ensures Gemma 4 models operate corr
This release candidate fixes a Windows-specific issue where the llama-server process wasn't being properly terminated during cleanup operations. The fix addresses GitHub issue #16458 and improves the
arXiv:2606.03635v1 Announce Type: cross Abstract: Understanding short online videos involves more than identifying visible objects and actions; video makers often include an underlying message or purp
arXiv:2606.03273v1 Announce Type: cross Abstract: Visual DeepSearch requires multimodal large reasoning model (MLRM) agents to answer complex visual queries by repeatedly inspecting image regions, gro
arXiv:2512.22539v2 Announce Type: replace-cross Abstract: While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively und
arXiv:2606.03954v1 Announce Type: new Abstract: As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible conse
arXiv:2603.04444v3 Announce Type: replace-cross Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- se
arXiv:2603.04956v2 Announce Type: replace Abstract: This paper considers the problem of converting a given dense linear layer to low precision. The tradeoff between compressed length and output discre
arXiv:2509.19305v2 Announce Type: replace-cross Abstract: Diffusion probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. Howev
We partnered with @FireworksAI_HQ to train open-source models for legal. Here's what we found: 1) Hybrid legal agents can beat frontier models on quality and cost by routing selectively to a frontier
We’re bringing new capabilities to GPT-Rosalind, a model series purpose-built for life sciences research at enterprise scale. It brings GPT-5.5’s agentic coding and tool use together with stronger int
arXiv:2606.02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceed
arXiv:2606.03461v1 Announce Type: new Abstract: Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficult
arXiv:2606.03391v1 Announce Type: cross Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing mergi
arXiv:2606.03532v1 Announce Type: cross Abstract: Self on-policy distillation trains a student policy against a teacher derived from its own parameter history, yet the teacher's update schedule -- whi
arXiv:2606.03837v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) and probing enable adaptation of foundation models using only a small number of trainable parameters, making it a
arXiv:2606.02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-regis
arXiv:2602.08873v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now used for academic expert recommendation. Existing audits typically evaluate such recommendations in isola
arXiv:2606.03038v1 Announce Type: new Abstract: Neural field surrogates can accelerate photonic design loops, but a surrogate that looks accurate in global field error can still mis-rank candidate dev
arXiv:2503.07265v4 Announce Type: replace-cross Abstract: Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evalua
This post documents a completed Wordle puzzle (puzzle #1,809) solved in five attempts, showing the progression of letter guesses through color-coded feedback (yellow for correct letters in wrong posit
arXiv:2606.02908v1 Announce Type: cross Abstract: Multi-turn user-facing agents must infer user intent from incomplete requests, collect missing information through dialogue and tools, and execute val
arXiv:2606.00489v1 Announce Type: new Abstract: Placenta Accreta Spectrum (PAS) is a rare but highly dangerous obstetric disease. Early and accurate PAS diagnosis is critical for maternal health. Trad
arXiv:2606.01057v1 Announce Type: cross Abstract: Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neur
arXiv:2606.01933v1 Announce Type: new Abstract: This paper presents our winning methodology for the CASTLE 2026 Challenge at the CVPR 2026 EgoVis Workshop, where our team secured third place globally.
arXiv:2606.01973v1 Announce Type: cross Abstract: Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes. While recent methods have m
arXiv:2606.00821v1 Announce Type: new Abstract: This study addresses the challenge of controlling a complex, multi-parameter technological process -- pectin hydrolysis--extraction -- using machine lea
arXiv:2606.01034v1 Announce Type: new Abstract: We study when LLM judge panels should be calibrated with low-dimensional stackers versus joint output tables under finite human-label budgets. Low-dimen
arXiv:2606.02398v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation,
arXiv:2606.00922v1 Announce Type: cross Abstract: In this work, we propose a prototype machine-to-machine (M2M) knowledge-guided Large Language Model (LLM) framework for automated radiotherapy treatme
arXiv:2606.00106v1 Announce Type: cross Abstract: Brain-computer interfaces (BCIs) are limited by low signal-to-noise ratio in modalities such as electroencephalography, which requires multiple trials
arXiv:2606.00027v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed across healthcare, yet existing benchmarks fail to capture model behavior under adversarial or
arXiv:2507.12645v1 Announce Type: cross Abstract: The increasing need for accurate and unified analysis of diverse biological signals, such as ECG and EEG, is paramount for comprehensive patient asses
arXiv:2606.01122v1 Announce Type: new Abstract: We propose a five-step diagnostic protocol for residual-trained neural HJB-PIDE solvers with control-dependent Levy jumps, targeting a general failure m
arXiv:2606.01992v1 Announce Type: cross Abstract: Industrial anomaly detection has historically been a unimodal task. Recent multimodal vision-language models have produced systems that admit textual