Knowledge catalogue
arXiv:2608.28944v1 Announce Type: new Abstract: Credit risk analysis in financial institutions traditionally requires analysts to manually write SQL queries, run statistical computations, and build vi
arXiv:2608.30952v1 Announce Type: cross Abstract: Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for
arXiv:2603.08814v2 Announce Type: replace-cross Abstract: Long-horizon task planning for heterogeneous multi-robot systems is essential for deploying collaborative teams in real-world environments; ye
arXiv:2608.30277v1 Announce Type: new Abstract: The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing th
arXiv:2602.13551v3 Announce Type: replace Abstract: Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant L
arXiv:2512.02337v2 Announce Type: replace Abstract: Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capabil
arXiv:2608.29530v1 Announce Type: cross Abstract: Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled
arXiv:2608.31084v1 Announce Type: new Abstract: The Jacobian Lens (J-lens) is a recent tool for interpreting LLMs. It reads a hidden state as a ranked list of vocabulary tokens, leaving multi-token co
arXiv:2608.29363v1 Announce Type: new Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands o
arXiv:2608.29241v1 Announce Type: new Abstract: Clinical voice agents are now deployed in routine care, where real patients do not wait their turn: they interrupt. These systems typically use a cascad
arXiv:2608.29571v1 Announce Type: new Abstract: Flexible adaptation to context and shared pragmatic intuitions contribute to smooth human conversation. Iterated reference games---in which players repe
arXiv:2608.28293v1 Announce Type: new Abstract: The premise and promise of KV (cache) eviction is simple: higher throughput can be achieved by evicting some entries from the KV cache, at a negligible
arXiv:2608.28491v1 Announce Type: cross Abstract: Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet monolithic pixel models entangle the
arXiv:2608.27497v1 Announce Type: new Abstract: Recent embodied models increasingly leverage geometric representations to improve spatial reasoning and robotic manipulation. However, existing reconstr
Many of the questions that matter in enterprise data aren't just about individual rows — they're about how things connect: how two accounts are linked, what path a payment took, what context grounds a
This post builds an enterprise agentic retrieval solution on the Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore. An agent reasons, routes across multiple knowledge bases, and retur
arXiv:2608.27513v1 Announce Type: new Abstract: Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models
arXiv:2608.27974v1 Announce Type: new Abstract: Data annotation remains a central bottleneck in natural language processing, requiring human effort to obtain high-quality labels at scale. While Large
Hey guys, I tested Qwen3.8 Flash with llama.cpp from CPU-only to the full 96GB of my RTX PRO 6000. Short version: CPU-only reached 8.34 tok/s at a 2K prompt Full 96GB reached 109.07 tok/s At 245K cont
arXiv:2608.27481v1 Announce Type: new Abstract: Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually tr
I built SpeakoFlow Mini, an Apache-2.0 fine-tune of Qwen3.5-0.8B for dictation cleanup. It is not a chat model or a general rewriter. It takes speech-to-text output, applies corrections the speaker ac
OpenAI announced ChatGPT Work on July 9th, and have been furiously iterating on it ever since. It is an extraordinarily confusing and very powerful product. Here's what I've figured out about it so fa
Below are the benchmark results for running Qwen3.8-Flash-Next on Strix Halo using the Vulkan backend of llama.cpp, combined with MTP model. Hardware Item Details CPU AMD Ryzen AI MAX+ 395 (16C/32T) G
arXiv:2608.26949v1 Announce Type: new Abstract: Answering questions over real-world documents requires processing long inputs that interleave text with tables. Optical context compression, which repre
arXiv:2608.26623v1 Announce Type: new Abstract: LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely un
arXiv:2608.26178v1 Announce Type: new Abstract: There is growing interest in whether language models have stable preferences, for technical, safety, and philosophical reasons. We test 20 language mode
arXiv:2608.26291v1 Announce Type: new Abstract: Mentalization - the ability to infer others' beliefs and intentions to guide one's own choices - is a key cognitive function underlying human social int
arXiv:2608.26716v1 Announce Type: new Abstract: Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic desig
arXiv:2608.27167v1 Announce Type: new Abstract: An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked
arXiv:2608.26990v1 Announce Type: new Abstract: Large language models can summarize financial information, but an operational stock-research system must first assemble heterogeneous evidence, expose u
arXiv:2608.26310v1 Announce Type: new Abstract: Large language models can now generate complex, multi-step mathematical proofs, but reliably determining their correctness and localizing early logical
arXiv:2608.26676v1 Announce Type: cross Abstract: Pruning is a practical approach to compress large language models (LLMs), but it can amplify text degeneration, especially repetition loops, even when
arXiv:2505.15740v2 Announce Type: replace-cross Abstract: Formal methods play a crucial role in ensuring the reliability of critical systems through rigorous mathematical verification. However, their
The initial reason for this was the Comfy H3 Sync & Sound Community Challenge: Comfy H3 Sync Sound Community Challenge! - by Allyson Toy I made a short rap track in Suno, then used Hermes Agent to bui
arXiv:2608.26982v1 Announce Type: new Abstract: Large language model (LLM) judges are increasingly used across various evaluation scenarios, making their judgment capabilities valuable intellectual pr
arXiv:2606.21891v2 Announce Type: replace Abstract: Scientific discovery can be formulated as an iterative search process over the space of hypotheses and experiments. Contemporary methods navigate th
arXiv:2608.26145v1 Announce Type: new Abstract: Our research focuses on evaluating literature reviews generated in short and long context settings of large language models (LLMs) to investigate the im
arXiv:2608.26848v1 Announce Type: cross Abstract: Medical Visual Question Answering (Med-VQA) holds significant promise for clinical decision support, yet faces challenges due to limited annotated dat
arXiv:2608.27206v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation
arXiv:2608.26190v1 Announce Type: new Abstract: World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primaril
arXiv:2608.26626v1 Announce Type: cross Abstract: This report presents a framework to help organisations, policymakers and researchers reason about the risks that emerge when AI agents interact with e
arXiv:2608.26160v1 Announce Type: new Abstract: Nowadays semantic models provide limited support for representing distributed AI workflows and their execution across heterogeneous edge, fog, and cloud
arXiv:2603.09215v2 Announce Type: replace Abstract: Interleaved spoken language models (SLMs) alternately generate text and speech tokens, but decoding at full transformer depth for every step becomes
arXiv:2608.26139v1 Announce Type: cross Abstract: Large Language Models demonstrate remarkable syntactic fluency, yet the optimization dynamics governing their acquisition of deep semantic dependencie
arXiv:2608.27127v1 Announce Type: new Abstract: Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cul
arXiv:2608.25344v1 Announce Type: new Abstract: Perceived risk in driving evolves over time and may be supported by specific scene entities, yet supervision is typically limited to coarse video-level
arXiv:2608.25023v1 Announce Type: cross Abstract: Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying v
arXiv:2608.25243v1 Announce Type: new Abstract: Continual knowledge injection is essential for keeping large language models up-to-date in a fast-evolving world. Existing methods rely on supervised fi
arXiv:2601.04879v2 Announce Type: replace Abstract: Synthesizing informative commercial reports from massive and noisy web sources is critical for high-stakes business decisions. Although recent deep
arXiv:2608.25936v1 Announce Type: cross Abstract: On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of
arXiv:2608.26091v1 Announce Type: cross Abstract: Civil infrastructure compliance checking has long relied on engineers manually reading legacy 2D plans; however, OCR-based automation strips away the
arXiv:2608.25922v1 Announce Type: new Abstract: GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reas
I hit my token limit three times a day on my max subscription - got sick of that and designed this MCP setup to shift some of the coding load to my local Qwen3.8-27B model. I've been iterating on it n
arXiv:2608.26067v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a sin
arXiv:2608.25756v1 Announce Type: new Abstract: Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most ef
arXiv:2603.02203v2 Announce Type: replace-cross Abstract: Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for Recursive Self-Improving AI (RSI) by adapting Large Reasoning
arXiv:2608.25580v1 Announce Type: new Abstract: Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or
I've been building this for my own work but there's no reason for it to stay private, so here it is.Visionary is a single Modal app that gives you Krea 2 for stills, MiniMax-H3 for video-with-sound, a
arXiv:2608.23572v1 Announce Type: cross Abstract: We propose a novel framework for the analysis of multimodal data -- encompassing visual, auditory, and spatial stimuli -- foregrounding the role of co
arXiv:2608.23892v1 Announce Type: cross Abstract: This article presents the abridged core of A Mathematical Theory of Interpretation (MTI), which treats interpretation as observer-relative spectral me