Knowledge catalogue
arXiv:2608.10279v1 Announce Type: cross Abstract: Streaming language-model output creates a release-timing problem: complete-response moderation acts after streamed text has escaped, whereas repeated
arXiv:2506.02594v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to synthesize heuristic programs, yet most existing pipelines optimize solvers against fixed benc
arXiv:2512.02436v2 Announce Type: replace Abstract: Prediction markets allow users to trade on outcomes of real-world events, but are prone to fragmentation with overlapping questions, implicit equiva
arXiv:2608.09638v1 Announce Type: new Abstract: Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reason
arXiv:2608.09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expecte
arXiv:2512.11614v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on retrieved context to guide large language models (LLM), yet treats the retrieval as a heuristic
Back after ~6 months — rebuilding my spiking language model around CPU-first inference Hey everyone. It’s been around six months since I last posted anything about this project here. Some of you might
arXiv:2608.09324v1 Announce Type: new Abstract: On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding th
arXiv:2608.09024v1 Announce Type: new Abstract: Emergency-department (ED) triage requires clinicians to rapidly identify patients who need immediate attention, determine who can safely wait, and prior
arXiv:2508.17092v2 Announce Type: replace-cross Abstract: Knowledge Tracing (KT) aims to predict a student's future performance based on their sequence of interactions with learning content. Many KT m
arXiv:2608.09096v1 Announce Type: new Abstract: Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emergi
arXiv:2511.18852v2 Announce Type: replace Abstract: Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on gener
arXiv:2608.08395v1 Announce Type: cross Abstract: Generative AI is shifting digital commerce from browsing toward agentic search, in which consumers delegate product discovery to AI agents. We compare
arXiv:2608.09921v1 Announce Type: new Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power s
arXiv:2604.02047v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward p
arXiv:2608.08447v1 Announce Type: cross Abstract: Multilingual reasoning models are commonly evaluated by whether they arrive at the correct answer, but not by whether they preserve the intended langu
arXiv:2608.09031v1 Announce Type: new Abstract: Graph neural networks typically propagate information through repeated message-passing layers, coupling the distance over which information travels with
arXiv:2607.10194v2 Announce Type: replace-cross Abstract: We present IsalHG, a method for representing the structure of any finite, connected hypergraph of bounded hyperedge arity as a string over a c
arXiv:2608.07763v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance on tasks such as image captioning, visual question answering, and image-to-text generatio
arXiv:2608.09083v1 Announce Type: new Abstract: Estimating human joint torques from visual observations is a key step toward bringing biomechanical analysis from controlled laboratories to real-world
arXiv:2508.03875v2 Announce Type: replace Abstract: Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas oth
Testing with 3-5 agents. Decode performance is superb, however if one performs a web search and needs to process a few thousand tokens, ALL other agents will grind to a halt: I've tried tuning a littl
arXiv:2508.09125v4 Announce Type: replace Abstract: Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabili
Hey everyone, Today we release Luth-2-0.8B and Luth2-2-2B, two non-reasoning models that set a new state of the art for French across a wide variety of tasks for their size 🚀 A few notable scores on F
arXiv:2608.09696v1 Announce Type: new Abstract: Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a mechanistic, causal model, not a c
arXiv:2608.08118v1 Announce Type: new Abstract: There are several methods for searching for graphs with prescribed properties, such as SAT solvers and specialized generators. These methods return the
arXiv:2608.09176v1 Announce Type: cross Abstract: Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize
arXiv:2608.09666v1 Announce Type: new Abstract: Recent advances in visual generative models have enabled high-quality image and video generation, but evaluating these models often demands sampling hun
arXiv:2607.16235v3 Announce Type: replace-cross Abstract: Mobile and wearable devices offer an unprecedented opportunity for continuous, passive health monitoring and active health coaching. However,
arXiv:2608.08557v1 Announce Type: new Abstract: Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing
arXiv:2608.08311v1 Announce Type: cross Abstract: We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits
arXiv:2608.09931v1 Announce Type: new Abstract: Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Dist
arXiv:2608.09123v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy multidimensional criteria without following a s
arXiv:2608.08106v1 Announce Type: new Abstract: Synthetic Aperture Sonar (SAS) is core for wide-area detection of small underwater targets. However, large-scale, high-quality SAS datasets are scarce,
arXiv:2608.07835v1 Announce Type: new Abstract: Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes su
arXiv:2601.18077v3 Announce Type: replace Abstract: Cooperative reasoning under incomplete information remains challenging for both humans and multi-agent systems. The card game Hanabi embodies this c
arXiv:2505.11480v4 Announce Type: replace-cross Abstract: Superoptimization is the task of transforming a program into a faster one, and ideally the very fastest possible one, while preserving its inp
arXiv:2608.08528v1 Announce Type: new Abstract: Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries,
arXiv:2608.08290v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) repurposes a pretrained CLIP encoder for dense prediction without additional labeled supervision. Existing
arXiv:2608.07917v1 Announce Type: new Abstract: Chinese historical documents preserve valuable cultural heritage, but many collections remain accessible only as scanned page images, preventing full-te
arXiv:2608.08907v1 Announce Type: cross Abstract: Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then
arXiv:2608.08795v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external o
arXiv:2608.07700v1 Announce Type: new Abstract: Translating a natural-language question into a SPARQL query that can be executed against a large knowledge graph requires resolving lexical ambiguity, g
arXiv:2506.01952v2 Announce Type: replace-cross Abstract: Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent
arXiv:2608.07538v1 Announce Type: new Abstract: As LLM agents move from decision support to autonomous procurement, firms need to know whether delegated negotiators create value, divide it predictably
Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like a
arXiv:2505.11146v3 Announce Type: replace-cross Abstract: Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant
arXiv:2608.08929v1 Announce Type: new Abstract: 2D affordance grounding aims to locate the region of an object that a human can interact with. Existing research focuses on recognizing affordance types
arXiv:2608.06772v1 Announce Type: new Abstract: Accurate estimation of building energy use is essential for achieving carbon neutral and sustainable buildings. To better understand the influence of de
arXiv:2608.07157v1 Announce Type: new Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by
I've been comparing Cline / Kilo / Qwen Code lately since they all handle long-task state differently. Cline: has Focus Chain, a markdown file kept outside the conversation that gets reinjected on a c
arXiv:2608.06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration
arXiv:2608.06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world s
arXiv:2608.07147v1 Announce Type: new Abstract: Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from co
arXiv:2608.06381v1 Announce Type: cross Abstract: Explainable AI (XAI) has shown promise for human-agent collaboration, yet results rely on hand-crafted policies in custom environments, limiting gener
arXiv:2608.07437v1 Announce Type: new Abstract: Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate t
arXiv:2608.06984v1 Announce Type: cross Abstract: Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts. However,
arXiv:2608.06580v1 Announce Type: new Abstract: Face Recognition (FR) systems in surveillance settings often encounter Low Resolution (LR) faces, those whose face region falls below the standard 112 i
arXiv:2607.09885v2 Announce Type: replace Abstract: We present Index-1.9B, a series of open small language models developed at Bilibili. The series comprises four models: Index-1.9B-Base, a foundation
arXiv:2608.07079v1 Announce Type: cross Abstract: Object-goal navigation has made substantial progress in semantic perception and exploration, yet persistent memory for multi-object navigation and cro