Knowledge catalogue
I'm currently testing out Qwen3.8-27B using Unsloth's UD-Q4_K_XL running a freshly rebuilt llama.cpp. I have a 22GB RTX 2080TI on which I'm able to fit 100k context with q8_0 quantization, and using M
arXiv:2608.11292v1 Announce Type: new Abstract: Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The c
The way most people leverage test-time compute today is via a form of test-time NL reasoning that is computationally equivalent to test-time search (sometimes with a verifier / grader in the loop). Th
arXiv:2608.10864v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong image and video understanding, yet their visual-spatial representations remain geometrically fragile,
arXiv:2608.08648v1 Announce Type: new Abstract: Whole-slide visual reasoning requires identifying sparse diagnostic evidence in gigapixel pathology slides and integrating observations across spatial s
arXiv:2608.09333v1 Announce Type: new Abstract: Large-scale language models for autonomous driving enable enhanced global understanding and long-horizon planning. However, when deployed in isolated ve
arXiv:2505.24273v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) suggest that reinforcement learning (RL) effectively internalizes search strategies, yielding si
arXiv:2608.09818v1 Announce Type: cross Abstract: Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-
arXiv:2608.08514v1 Announce Type: new Abstract: We independently reproduce two recent methods for making large language model (LLM) reasoning more reliable, and stress-test them across domains and mod
Will Knight / Wired: Researchers find that feeding a frontier model's encrypted reasoning traces to a weaker model from the same provider can make it output the traces in plaintext — Researchers devis
arXiv:2505.15062v5 Announce Type: replace-cross Abstract: Knowledge extrapolation is the process of inferring novel information by combining and extending existing knowledge that is explicitly availab
arXiv:2608.09873v1 Announce Type: cross Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It co
arXiv:2608.09682v1 Announce Type: new Abstract: Tool-augmented vision-language models increasingly 'think with images': they call crop, zoom, or code tools and reason over the returned pixels. However
arXiv:2608.06243v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcom
arXiv:2608.05565v1 Announce Type: new Abstract: Video object removal must eliminate not only the target object but also its induced effects while maintaining high-fidelity and spatiotemporally coheren
OpenAI announced that Plus and Pro subscribers now have a slider to adjust the amount of reasoning effort ChatGPT applies to each response. The update employs GPT‑5.6 Sol for both Instant and deep rea
arXiv:2608.04424v1 Announce Type: new Abstract: Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reaso
We’re making better intelligence easier to access in ChatGPT for everyone: - GPT-5.6 Sol now powers both Instant and deep reasoning for Plus & Pro users, delivering more factual, focused responses. -
arXiv:2608.04726v1 Announce Type: new Abstract: Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usual
arXiv:2608.03068v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, exis
arXiv:2608.03882v1 Announce Type: cross Abstract: Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logis
arXiv:2608.02993v1 Announce Type: new Abstract: (Flat) Reinforcement Learning (RL) agents face significant challenges in environments with sparse rewards that require long-horizon reasoning. A compell
arXiv:2608.03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: se
arXiv:2511.21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies. We stu
arXiv:2608.03763v1 Announce Type: new Abstract: Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existin
arXiv:2608.00542v1 Announce Type: new Abstract: Graphs model relational data throughout science and industry, from citation networks to product co-purchase graphs. Because the nodes of many such graph
arXiv:2608.01575v1 Announce Type: new Abstract: Whether large language models perform genuine algorithmic reasoning or mere pattern completion is hard to test, because most benchmarks lack a ground tr
arXiv:2608.00100v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly being evaluated for medical imaging, but many available benchmarks emphasize disease classification, repo
arXiv:2601.15297v3 Announce Type: replace Abstract: Reliable question answering over long institutional documents requires more than topical retrieval: a system must localize the exact passage that su
arXiv:2607.28460v1 Announce Type: new Abstract: A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day.
arXiv:2607.24833v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is a powerful paradigm for eliciting reasoning in large language models, yet it suffers from severe rewar
arXiv:2607.25145v1 Announce Type: cross Abstract: We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in d
arXiv:2607.25933v1 Announce Type: cross Abstract: Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practic
arXiv:2605.04330v2 Announce Type: replace Abstract: We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelati
arXiv:2511.02130v2 Announce Type: replace-cross Abstract: We propose Re-FORC, an adaptive reward prediction method that, given a query, enables prediction of the expected future rewards as a function
arXiv:2607.20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocate
arXiv:2604.02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safet
arXiv:2607.20402v1 Announce Type: new Abstract: In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensional inputs. Further, the predicate
arXiv:2607.13454v1 Announce Type: cross Abstract: Although multimodal large language models (MLLMs) have achieved remarkable progress, understanding 3D spatial relationships from 2D images remains a c
arXiv:2607.13860v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in 2D medical image understanding, their extension to 3D volumetric
arXiv:2607.13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task act
arXiv:2607.08758v1 Announce Type: new Abstract: Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biol
arXiv:2607.07883v1 Announce Type: new Abstract: There is relatively little, public, and model-ready data on industrial machinery for African economies. This makes it hard to do quantitative analysis o
One of the most confusing aspects of GPT-5.6 is figuring out which model to use at which reasoning effort - sounds like Sol on Medium might be a good new default for coding work, if it's an upgrade fr
arXiv:2601.02918v3 Announce Type: replace Abstract: Image Quality Assessment (IQA) is a long-standing problem in computer vision. Previous methods typically focus on predicting numerical scores withou
arXiv:2607.07601v1 Announce Type: cross Abstract: Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize co
arXiv:2602.14147v2 Announce Type: replace Abstract: Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multi
arXiv:2607.05861v1 Announce Type: new Abstract: Large reasoning models (LRMs) improve language model capabilities by generating explicit thinking traces before final answers. In factuality-oriented qu
arXiv:2607.05911v1 Announce Type: new Abstract: Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pa
arXiv:2607.05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often re
arXiv:2607.04162v1 Announce Type: cross Abstract: Open-ended tabletop manipulation requires agents to not only understand natural language but also adapt to dynamic environments and execution failures
arXiv:2607.03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason. We introduce NormWorlds-CF, a solver-verified environment for counterfactu
arXiv:2607.02869v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models. Yet m
arXiv:2607.03069v1 Announce Type: new Abstract: As video generation paradigms evolve from localized manipulation to full-scene synthesis, AI-generated video detection becomes increasingly challenging,
arXiv:2607.02922v1 Announce Type: new Abstract: Video reasoning segmentation demands pixel-accurate object tracking across hundreds of frames under complex natural language queries, producing dense sp
arXiv:2508.01858v3 Announce Type: replace-cross Abstract: Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital envi
This post discusses how observing Claude's internal activation patterns (J-space) reveals the model's hidden reasoning processes, such as detecting code bugs and analyzing images, even when these step
arXiv:2607.00147v1 Announce Type: new Abstract: Rare disease differential diagnosis is a critical yet arduous clinical task, requiring physicians to identify precise phenotypes from complex, unstructu
arXiv:2508.01273v3 Announce Type: replace Abstract: Explicit knowledge conflicts, occurring when retrieved contexts contain contradictory information, pose a fundamental challenge for Large Language M
arXiv:2512.21002v3 Announce Type: replace-cross Abstract: Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of re