Knowledge catalogue
arXiv:2607.21613v1 Announce Type: cross Abstract: We investigate where and how transformer-based language models commit to predictions in multiple-choice question answering. We identify the _Hard Deci
--> .abbel-fig { display: block; text-align: center; margin: 2.4em 0; line-height: 1.4; max-width: 100%; } .abbel-fig img { display: block; margin: 0.65em auto 0; height: auto; max-width: 100%; } /* I
training to benchmarks ≠ getting to AGI This suggests that Opus 5 's gain on ARC-AGI-3 was the result of specific training to improve on that eval, and not a generalized increase in abstract reasoning
Hi everyone, I have a system which I have been using for gaming, R7 5700X, 48GB DDR4, RTX3090 24GB. But I want to use it for Local AI to reduce my reliance on cloud AI providers (mainly usage limits -
Ha! It did it: 'We introduce BenchBenchBenchBenchBench (BBBBB), an executable benchmark of AI-authored conformance suites for benchmark-evaluation metrics' I really thought it would treat 'now do benc
arXiv:2607.21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that req
arXiv:2607.21155v1 Announce Type: cross Abstract: Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiri
arXiv:2607.21013v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new leve
arXiv:2607.20489v1 Announce Type: new Abstract: Text-to-SQL has advanced rapidly with large language models, but complex database queries still require reasoning beyond one-shot generation, including
So I've taken some time to actually test laguna on a few of my own projects. I wanted to share as I feel most peoples comments at this point have just been about getting it running or saying it doesnt
arXiv:2607.20539v1 Announce Type: cross Abstract: While deep learning has accelerated drug discovery, its impact on biomanufacturing has been considerably more limited. The reason is data scarcity. Bi
arXiv:2607.20507v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these applic
arXiv:2607.20908v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code
arXiv:2607.20517v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) over heterogeneous PDF collections remains challenging due to multimodal content, domain-specific terminology, and
arXiv:2607.21557v1 Announce Type: new Abstract: Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to e
arXiv:2607.20506v1 Announce Type: new Abstract: GraphRAG enables deeper reasoning by structuring knowledge as graphs but struggles with n-ary facts. HyperGraphRAG uses hypergraphs for richer semantics
Our team just shipped Fugu-Ultra v1.1! 🐡 By dynamically orchestrating the latest frontier models, we pushed performance up by 7.9 points. We are now beating Fable 5 in complex coding and reasoning tas
arXiv:2607.21179v1 Announce Type: new Abstract: The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly ove
arXiv:2607.20925v1 Announce Type: new Abstract: AI knowledge systems require representations of entity importance for retrieval, recommendation, evidence selection, and knowledge-intensive reasoning.
arXiv:2607.21447v1 Announce Type: cross Abstract: The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate
arXiv:2607.16619v2 Announce Type: replace Abstract: Safe and socially compliant navigation in open human-robot environments requires robots to reason about heterogeneous participants with different dy
arXiv:2607.21307v1 Announce Type: cross Abstract: The reliance on unstructured free text for documenting clinical trial protocols creates a significant barrier to automated reasoning, cohort discovery
arXiv:2607.21072v1 Announce Type: new Abstract: Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks a
https://huggingface.co/swiss-ai/Apertus-v1.5-70B https://huggingface.co/swiss-ai/Apertus-v1.5-8B Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multil
arXiv:2512.19178v2 Announce Type: replace-cross Abstract: Bridging the gap between natural language commands and autonomous execution in unstructured environments remains an open challenge for robotic
We benchmarked Opus 5 comprehensively on document understanding through ParseBench. It is roughly on par with Opus 4.8 - it does a few points worse on dense tables, but does slightly better on parsing
arXiv:2607.18034v2 Announce Type: replace Abstract: Smart home assistants interpret a wide range of user commands, from explicit device control to underspecified and preference dependent requests. Whi
AI9Stars has released G9v3-3B an open weights language model designed to deliver strong reasoning capabilities within a lightweight 3 billion parameter size. It is released under the Apache 2.0 licens
Fix DeepSeek4 crafted template (#25414) chat: fix DS4 template to explicitly follow reference behavior Support DeepSeekv4 flag (drop_reasoning). fix: hook DS3.2 parser for DS4 as well fix: add tool re
In this post, we explore how Jefferies overcame these challenges with a solution built on Strands Agents, an agent harness SDK for building AI agents that can reason, plan, and act by orchestrating ca
arXiv:2607.19374v1 Announce Type: new Abstract: Recent formal reasoning systems have reached IMO-level performance, yet they leave a fragmented landscape: algebra and number theory are handled in Lean
arXiv:2607.19911v1 Announce Type: new Abstract: Long-range vehicle trajectories provide important spatio-temporal evidence for traffic safety analysis, autonomous driving evaluation, and data-driven t
arXiv:2604.03447v2 Announce Type: replace-cross Abstract: LLM-based software engineering assistants often reason over multiple artifacts, including code, documentation, signatures, and tests, even whe
arXiv:2607.19339v1 Announce Type: new Abstract: Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve wit
arXiv:2607.19261v1 Announce Type: new Abstract: Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scal
arXiv:2603.16827v2 Announce Type: replace Abstract: Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language models (LLMs) often exhibit cultural biases that
arXiv:2607.19949v1 Announce Type: new Abstract: Smartphone personal assistants reason over longitudinal personal data, yet evaluating them requires context-rich evaluation data whose correct answers a
arXiv:2607.20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language
arXiv:2607.19901v1 Announce Type: new Abstract: Deep learning frameworks like nnU-Net achieve state-of-theart brain lesion segmentation performance but remain difficult to deploy in clinical research
My 2hr workshop on Open vs Closed models, reward hacking, benchmaxxing & RL is out! 1. Closed vs open models 2. Throughput maxxing but accuracy minimizing 3. Benchmaxxing & cheating 4. Distillation &
TL;DR: I’m reproducing the trait-persistence result from arXiv:2606.24014 on one RTX 3090. Before I can test persistence I need to install a trait via RL — and my GRPO run moves the trait only +2.4 po
arXiv:2607.13940v1 Announce Type: new Abstract: Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an ope
arXiv:2607.13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding. We audit this assumption across twenty
arXiv:2607.13260v1 Announce Type: cross Abstract: Policy documents shape governance outcomes, but their reasoning is often implicit. Participatory commitments and managerial control routinely coexist
arXiv:2508.12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting vi
arXiv:2601.12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content a
arXiv:2607.13051v1 Announce Type: cross Abstract: TriAttention is a recent method for shrinking the KV cache of long-reasoning LLMs: it scores each cached key by how much attention it is likely to rec
arXiv:2607.13681v1 Announce Type: new Abstract: Humans can efficiently parse continuous sensory streams, from hours to years, scaffolding an internal world model that grounds spatial reasoning and pre
What's Changed Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations Fixed a recurrent MLX model cache leak that could increase memory use across
arXiv:2607.13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pi
arXiv:2607.12640v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkp
arXiv:2607.10350v1 Announce Type: cross Abstract: Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime la
LLMs handle speech well once you run speech-to-text. They don't hear the rest: a bird outside, a glass breaking two rooms away, a smoke alarm two floors down. I've been working on an experimental open
arXiv:2511.23276v2 Announce Type: replace Abstract: Effective HFMD surveillance requires forecasts capturing both time-series patterns and contextual drivers such as school calendars, weather, and pol
arXiv:2607.11263v2 Announce Type: replace Abstract: Two competing perspectives on fluid intelligence (gf) measures propose that performance is primarily constrained either by working memory capacity o
arXiv:2509.21842v2 Announce Type: replace Abstract: Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generati
arXiv:2607.12787v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enab
arXiv:2602.15892v2 Announce Type: replace-cross Abstract: Visual perspective taking--inferring how the world appears from another's viewpoint--is foundational to social cognition. We introduce FlipSet
arXiv:2607.12463v1 Announce Type: new Abstract: Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in
Inkling is our first open model from @thinkymachines and is now available on Tinker! Check out these quotes from Tinker customers on their experience with Inkling: @_Mantic_AI: 'Not only does Inkling