Knowledge catalogue
arXiv:2608.24135v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has emerged as a pivotal technique for enhancing the code generation capabilities of Large Languag
arXiv:2608.24011v1 Announce Type: cross Abstract: Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typi
arXiv:2608.23873v1 Announce Type: new Abstract: Everything a language model sees is tokens. The serving stack knows what each span is -- user input, tool output, instructions -- but the model must kee
arXiv:2608.23840v1 Announce Type: cross Abstract: Training large-scale AI models often outgrows a single data center, demanding sharded, multi-cluster, and decentralized training. However, the huge sp
arXiv:2603.00188v2 Announce Type: replace-cross Abstract: Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing me
arXiv:2608.23752v1 Announce Type: cross Abstract: The growing size of Convolutional Neural Networks has led to increasingly large and costly models. Knowledge Distillation (KD) addresses this by trans
arXiv:2608.24626v1 Announce Type: new Abstract: Liver fibrosis, the principal predictor of long-term outcome in chronic liver disease, is staged from histological estimates of collagen content. Sirius
arXiv:2608.23763v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness int
arXiv:2606.18699v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal rea
I ran 11 uncensored variants of Gemma 4 12B that I grabbed from huggingface, sorting by downloads. 10 full abliterations plus 2 LoRA adapters which were requested to be added in the comparison, agains
SemiAnalysis: A detailed look at Jalapeño, OpenAI's ASIC developed with Broadcom in 16 months, which beat Nvidia, AMD, and Google chips on multiple top open-weight models — OpenAI's self-designed ASIC
For two years, the field has gotten very good at training models, and it still hand-wires the agents around them. Whether an agent plans, searches, calls a tool, or checks its own work before answerin
arXiv:2608.21712v1 Announce Type: new Abstract: Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures still require substantia
arXiv:2608.21431v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information.
arXiv:2608.22762v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-h
arXiv:2608.22068v1 Announce Type: new Abstract: Geothermal well arrays, which organize multiple geothermal wells into carefully planned geometric configurations, provide opportunities to enhance energ
arXiv:2608.22695v1 Announce Type: cross Abstract: Agent ecosystems now include thousands of MATS components (Models, Agents, Tools, and Skills), yet their discovery still relies on in-context routing.
arXiv:2608.23497v1 Announce Type: new Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with
OpenWorker -- an open source agent that doesn't just chat but completes tasks on your laptop -- just released a new version with many features for security workflows. After our initial release, many u
arXiv:2608.21381v1 Announce Type: cross Abstract: Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across th
arXiv:2608.23048v1 Announce Type: new Abstract: Semi-structured N:M sparsity has emerged as a practical direction for accelerating large language models (LLMs). However, existing learnable-mask approa
TL;DR - A ~4M example, ~3B token CoT dataset designed around helping small models think more concisely, accurately and reliably. Hi all! For the past few months I have been working on a dataset design
arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph
arXiv:2608.22898v1 Announce Type: new Abstract: Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) large language models (LLMs), but their degraded gener
arXiv:2608.21610v1 Announce Type: new Abstract: Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, disc
arXiv:2608.21948v1 Announce Type: new Abstract: Complex clinical reasoning requires models to update diagnostic hypotheses as new evidence emerges and to coordinate different medical specialities unde
arXiv:2608.22752v1 Announce Type: new Abstract: A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budget overflows, both are summarized at the same rate;
arXiv:2608.23252v1 Announce Type: cross Abstract: As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of e
arXiv:2608.22127v1 Announce Type: new Abstract: Text-Attributed Graphs (TAGs) integrate graph structures and node-associated textual attributes, and recent studies have increasingly leveraged Large La
Source of Claims: https://x.com/Andy_ShuoYang/status/2090856976880472439 Your gaming PC can now serve frontier models at interactive speed using official checkpoints without extreme quantization! Qwen
arXiv:2608.20367v1 Announce Type: cross Abstract: Poultry production operates under tightly coupled environmental and biological dynamics, yet commercial climate control remains largely heuristic, lim
arXiv:2608.21186v1 Announce Type: new Abstract: Surgical procedures such as laparoscopic appendectomy are complex, high-stakes processes, yet formalizing their workflows for decision support remains a
arXiv:2608.20379v1 Announce Type: new Abstract: Advances in large language models (LLMs) have fueled a wave of research into agency: the ability to reason, plan, and act. This effort has produced agen
arXiv:2608.20566v1 Announce Type: new Abstract: AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, inv
arXiv:2608.20634v1 Announce Type: cross Abstract: Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around
arXiv:2508.14313v4 Announce Type: replace-cross Abstract: Test-time scaling strategies for Large Language Models predominantly rely on either reinforcement learning with sparse outcome rewards or sear
arXiv:2608.20637v1 Announce Type: cross Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable
arXiv:2608.20851v1 Announce Type: cross Abstract: Agentic engineering systems have shown strong performance on general-purpose benchmarks, yet their effectiveness in enterprise resource planning (ERP)
arXiv:2608.20649v1 Announce Type: new Abstract: Designers and policymakers in sociotechnical domains like content moderation, privacy interfaces, recommender systems and beyond, must choose among a gr
arXiv:2608.20768v1 Announce Type: new Abstract: Specialist language models are usually understood through endpoint gains: the generalist scores lower, the specialist scores higher, and the difference
arXiv:2608.21041v1 Announce Type: cross Abstract: Geospatial representation learning from satellite imagery is a fundamental problem for large-scale urban analysis and real-world applications. Despite
arXiv:2608.20864v1 Announce Type: new Abstract: Artificial Intelligence (AI) offers significant potential for future aviation systems; however, its integration into safety-critical applications requir
arXiv:2608.20970v1 Announce Type: new Abstract: Recent work in mechanistic interpretability has studied how large language models recall facts stored in their weights. This paper argues that factual r
arXiv:2608.20717v1 Announce Type: new Abstract: Reliable confidence estimation is essential for using large language models in mathematical reasoning, but black-box verbalized confidence is difficult
arXiv:2608.21043v1 Announce Type: new Abstract: Conventional in-distribution evaluation can overestimate robustness when training and test data share recurring task-specific patterns or surface cues.
arXiv:2505.11924v4 Announce Type: replace-cross Abstract: Intrinsic moral self-correction refers to the phenomenon where a language model refines its ethical judgments or aligns its outputs purely thr
arXiv:2608.20539v1 Announce Type: cross Abstract: Digital twin simulations show promise, but current empirical evidence suggests that the approach should be tested before being deployed in any particu
arXiv:2608.20572v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is
arXiv:2608.21233v1 Announce Type: new Abstract: The Traveling Salesman Problem (TSP) is one of the most extensively studied NP-hard optimization problems. Genetic Algorithm (GA)-based solvers, such as
arXiv:2608.20574v1 Announce Type: new Abstract: Open-ended language-model benchmarks usually inherit a judge: a human preference panel, another model, or a brittle exact-match key. We introduce Flavou
hello everyone. I'm training PPO variants on different multi-agent tasks from the VMAS library (Independent PPO / Graph PPO and such, see HetGPPO by Bettini et al.). I noticed that for every architect
Interesting new approach to enable memory in long-running agents. Weighted Memory Tree organizes execution into tasks, subtasks, and actions, then gives every memory a retention score that moves. Even
arXiv:2608.20988v1 Announce Type: cross Abstract: Quantization of Large Language Models (LLMs) is often hindered by the sensitivity of the self-attention mechanism to discretization errors. We identif
arXiv:2510.13922v2 Announce Type: replace-cross Abstract: Clinical notes contain unstructured text provided by clinicians during patient encounters. These notes are usually accompanied by a sequence o
arXiv:2608.20406v1 Announce Type: new Abstract: Public health forecasts must respond to abrupt changes in surveillance data without over-extrapolating noise, reporting artifacts, or temporary trends.
arXiv:2608.20755v1 Announce Type: new Abstract: Modern de novo design workflows generate many candidate protein binders, but wet-lab validation capacity remains limited, making shortlisting a major bo
arXiv:2608.20938v1 Announce Type: new Abstract: Evaluators often produce correct labels via flawed reasoning, a critical failure for agentic systems gating actions, routing reviews, or supplying train
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of c
arXiv:2608.21315v1 Announce Type: new Abstract: That a prompt's effect is not a property of the prompt is established: prompts optimised for one model degrade on another, and rankings reorder under ne
Thanks to Unsloth Dynamic 3.0 quants coming in slightly leaner and better preserved, I settled on Qwen 3.8 27B (`UD_Q4_K_XL`) at 100K context as my daily driver for Hermes Agent and OpenCode. On an RT