Knowledge catalogue
arXiv:2609.00830v1 Announce Type: cross Abstract: Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the vi
arXiv:2606.15932v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have substantially advanced text-to-code generation, many real programming tasks specify intent through visual ar
arXiv:2608.29114v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires agents to reason over accumulated observations while continuously exploring unseen regions. However, exi
arXiv:2608.28784v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently made strong progress in visual--linguistic understanding. However, their performance on text-cent
arXiv:2608.29352v1 Announce Type: new Abstract: Large Language Models (LLMs) still exhibit limited capability in following complex instructions. While existing approaches often rely on preference lear
arXiv:2608.29035v1 Announce Type: new Abstract: Emotion recognition in conversations is increasingly tackled with language models, but these models can be unstable and expensive to fine-tune or to pro
arXiv:2510.00628v3 Announce Type: replace-cross Abstract: Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their pre
arXiv:2603.14602v3 Announce Type: replace-cross Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-spec
arXiv:2608.28707v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with questi
arXiv:2603.25201v2 Announce Type: replace Abstract: Recent research points toward LLMs being manipulated through adversarial and seemingly benign inputs, resulting in harmful, biased, or policy-violat
arXiv:2608.30052v1 Announce Type: cross Abstract: When a generative search interface answers a commercial question, which market's products it names is decided before the model reasons about the produ
arXiv:2506.17251v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have achieved remarkable performance, the inherent stochasticity of their reasoning processes and varyin
arXiv:2305.12474v4 Announce Type: replace Abstract: Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensive
arXiv:2608.26747v1 Announce Type: new Abstract: Scientific LLM agents have shown promise in literature reasoning, tool use, and experiment planning, but it remains unclear whether they can autonomousl
arXiv:2608.27219v1 Announce Type: new Abstract: Mental health assessment relies on episodic self-report scales, which convert subjective states such as stress into numerical scores but provide only sp
arXiv:2608.26114v1 Announce Type: new Abstract: Calculation-intensive financial question answering requires exact reasoning over structured rates, temporal conditions, numerical formulas, and rule-bas
arXiv:2608.26357v1 Announce Type: new Abstract: Large language models (LLMs) exhibit uneven multilingual performance, especially when dealing with low-resource languages. Inference-time intervention o
arXiv:2608.26744v1 Announce Type: new Abstract: Zero-shot classification needs efficient label retrieval and fine-grained visual reasoning, yet discriminative and generative vision-language models fai
Smaller models still struggle with browser tasks that require open-ended research or deep reasoning. But many practical browser-automation workflows are much more procedural: extracting structured dat
arXiv:2608.26176v1 Announce Type: new Abstract: AI systems whose outputs inform real decisions, and increasingly consequential ones, require something that current documentation practice does not prov
arXiv:2608.27039v1 Announce Type: cross Abstract: Accurately forecasting the movement of people in complex scenes requires reasoning over the past and present state of the entire environment. In this
arXiv:2608.26887v1 Announce Type: new Abstract: LLMs are thought to track 'belief states,' i.e., running probability distributions over the latent variables that govern language (Shai et al., 2024; Sa
arXiv:2608.26142v1 Announce Type: cross Abstract: Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and implicit textual queries. While recent advance
arXiv:2608.26480v1 Announce Type: cross Abstract: Multi-agent large language model systems are widely reported to beat single-model baselines, but the evidence is mixed, and comparisons are usually co
arXiv:2601.13207v2 Announce Type: replace Abstract: Geo-localization aims to infer the geographic location where an image was captured using observable visual evidence. Traditional methods achieve imp
Since Qwen's dropped the Qwen4Exp architecture bomb that focus on offloading parameters to n-gram instead of pure mixture of experts, I dug into this and learned quite a lot. Here's the summary. Expec
arXiv:2511.05393v2 Announce Type: replace Abstract: Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs)
arXiv:2608.25832v1 Announce Type: new Abstract: Large language models access knowledge inconsistently across languages, but to what extent do they differ in their skill sets when interacting with diff
arXiv:2603.03297v2 Announce Type: replace Abstract: Test-time training (TTT) adapts large language models (LLMs) during inference using only unlabeled test inputs. Existing methods, however, face two
arXiv:2608.24024v1 Announce Type: new Abstract: Confidence-based voting aggregates parallel LLM rollouts by weighting each with internal signals such as token log probabilities, and has been actively
arXiv:2608.23632v1 Announce Type: new Abstract: Process supervision has improved mathematical reasoning, where intermediate steps are naturally expressed as chains of thought. In code generation, howe
I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims
In the past, I have use llama.cpp, but I read that the exl3 quantization format should give better precision, so I have tried exllamav3/tabbyAPI. It was able to write the shown simple HTML game withou
arXiv:2608.22806v1 Announce Type: new Abstract: Iterative preference optimization is essential for aligning Large Language Models on mathematical reasoning tasks, yet its efficiency is often throttled
arXiv:2608.21595v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning ability of vision-language models (VLMs), and diversifying the rollouts wit
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relianc
arXiv:2608.22854v1 Announce Type: new Abstract: Practical deployment of large language models (LLMs) requires families of post-trained variants---instruction-tuned, reasoning-tuned, and chat-style mod
arXiv:2608.21140v1 Announce Type: cross Abstract: Reliable spatial understanding is an important prerequisite for future medical vision-language systems that aim to support radiological report generat
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:2608.20920v1 Announce Type: new Abstract: Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory m
arXiv:2608.20549v1 Announce Type: new Abstract: Advances in multimodal large language models (MLLMs) are extending radiological artificial intelligence (AI) beyond task-specific image analysis toward
I was fascinated by Nanbeige's outstanding performance for its size, so I started digging into how much a model can improve its own representation just by looping over itself (for fun). My prototype w
Release: llm 0.33 My highlights from this release: Upgraded to the OpenAI Python library 3.x and switched the HTTP client dependency from httpx to httpx2. #1608, #1631 I shipped a quick 0.32.1 fix for
Hi, I have been using opencode with openrouter for quite a while now. Having read the success stories of using Qwen3.8-27B, I thought of trying it too. But every attempt has been a failure for me so f
Right now standard CoT is a one-way street. You generate forward, dump a pile of scratchpad tokens into the KV cache, and pray the model doesn’t hallucinate halfway through. On phones/laptops that cre
arXiv:2608.20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing
arXiv:2608.19737v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and im
arXiv:2608.18103v1 Announce Type: cross Abstract: Background: Mechanistic elucidation of traditional Chinese medicine (TCM) compound formulas remains a central challenge in the modernization of TCM. C
arXiv:2608.18165v1 Announce Type: new Abstract: Knowledge graphs modeled in RDF are powerful for describing static knowledge, but they cannot capture or reason about the dynamic behavior of physical s
arXiv:2608.18682v1 Announce Type: new Abstract: Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, a
arXiv:2608.18628v1 Announce Type: cross Abstract: Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking
arXiv:2608.17536v1 Announce Type: cross Abstract: Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor i
arXiv:2608.17950v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these dist
arXiv:2608.17535v1 Announce Type: new Abstract: Simultaneously reconstructing and understanding 3D environments is essential for embodied agents. Toward this goal, feed-forward semantic 3D Gaussian Sp
arXiv:2502.13428v2 Announce Type: replace-cross Abstract: This work investigates how to improve large language model (LLM)-based reasoning for knowledge base question answering (KBQA) via Monte Carlo
arXiv:2608.17741v1 Announce Type: new Abstract: OWL 2 DL ontologies, grounded in the description logic SROIQ, express large knowledge bases in biomedicine and the Semantic Web. Neuro-symbolic (NeSy) l
arXiv:2608.17129v1 Announce Type: new Abstract: Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home
arXiv:2608.14585v1 Announce Type: new Abstract: Euclidean geometry is a compelling testbed for AI reasoning, as it demands the combination of intuitive diagram understanding, axiomatic deduction, and
arXiv:2608.15703v1 Announce Type: new Abstract: Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As
arXiv:2509.20357v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models to use long chain-of-thought reasoning (CoT) in domains like mathematic