Knowledge catalogue
Another banger paper from Microsoft. Why it's a big deal: It teaches reasoning models to compress their own chain-of-thought mid-generation. The most interesting finding isn't the 2-3x memory savings
arXiv:2610.21060v1 Announce Type: cross Abstract: To address sparse terminal rewards in LLM arithmetic reasoning, we propose a Bellman-consistent trajectory RL method. Our framework introduces Traject
arXiv:2610.20781v1 Announce Type: cross Abstract: Image-to-text (I2T) understanding and text-to-image (T2I) generation are dual tasks in unified multimodal models (UMMs). Reconstructive post-training
arXiv:2610.20805v1 Announce Type: new Abstract: A reasoning trace retained at answer time plays two roles: it can raise accuracy, and it can compete with the current evidence when the two disagree. We
arXiv:2610.16713v1 Announce Type: cross Abstract: Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors. We examined when they help and ho
arXiv:2610.19754v1 Announce Type: new Abstract: Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing meth
arXiv:2610.20598v1 Announce Type: new Abstract: Achieving general spatial intelligence requires a unified understanding of both static 3D and dynamic 4D. However, we find that existing models struggle
.@NVIDIA Nemotron 3.5 Super VL is now live on Together AI. An open-weight multimodal model built for visual reasoning and always-on agents that see, reason, and act across documents, screens, and vide
arXiv:2610.20292v1 Announce Type: new Abstract: Reliable medical reasoning requires LLMs to dynamically access external biomedical evidence to improve factual trustworthiness and reasoning accuracy. H
arXiv:2610.19121v1 Announce Type: cross Abstract: Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models. However, existing methods can cause reaso
arXiv:2610.19476v1 Announce Type: cross Abstract: Post-training often improves the performance of large audio-language models on audio understanding and reasoning benchmarks. However, these improvemen
arXiv:2610.15403v1 Announce Type: cross Abstract: Crowdsourced disaster imagery provides timely, ground-level observations when conventional disaster mapping is delayed or incomplete, yet its geograph
arXiv:2606.13106v2 Announce Type: replace Abstract: Latent chain-of-thought compresses reasoning through continuous hidden-state recurrence, but existing approaches are difficult to optimize with stan
arXiv:2610.18369v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated promising capabilities for remote sensing reasoning, yet they frequently generate visually un
arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Exi
arXiv:2508.08833v4 Announce Type: replace-cross Abstract: Frontier large language models (LLMs) now reach near-ceiling accuracy on standard mathematical-reasoning benchmarks and gold-medal-level perfo
arXiv:2610.11592v1 Announce Type: new Abstract: Current frontier LLMs can theoretically process long contexts with 1M tokens or more. But to what extent can they go beyond simple retrieval and perform
arXiv:2610.12090v1 Announce Type: new Abstract: Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating c
arXiv:2610.10889v1 Announce Type: new Abstract: Vision-Language (VL) reasoning requires a model to both extract relevant and accurate information from an image (visual reasoning, VR), and to infer the
arXiv:2610.09804v1 Announce Type: new Abstract: Reinforcement learning is now central to eliciting reasoning in large language models, while in the popular algorithm Group Relative Policy Optimization
arXiv:2610.09427v1 Announce Type: new Abstract: World-Action Models (WAMs) utilize future visual prediction as an intermediate reasoning process to guide action generation. However, existing WAMs typi
arXiv:2610.06949v1 Announce Type: cross Abstract: Large audio language models answer questions about speech, sound, and music, yet their accuracy drops sharply on tasks that need fine-grained acoustic
arXiv:2610.08446v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physic
arXiv:2610.07473v1 Announce Type: new Abstract: Large language models show promise in clinical reasoning, but psychiatric interviewing requires guiding an evolving conversation. Their ability to carry
arXiv:2601.23027v2 Announce Type: replace Abstract: Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generatio
arXiv:2610.05715v1 Announce Type: new Abstract: Vision-language models (VLMs) can detect that an object has rotated across views, but cannot reliably tell by how much. We introduce OR-Bench, a fine-gr
arXiv:2610.03519v1 Announce Type: new Abstract: A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers
arXiv:2610.03329v1 Announce Type: cross Abstract: Large language models are increasingly used where small syntactic errors matter, yet character-level reasoning is still evaluated mostly through isola
Reasoning from scratch, round number 6! An introduction (and implementation) of Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO). 00:00 Introduction
arXiv:2610.01754v1 Announce Type: cross Abstract: Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and cu
arXiv:2610.01080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the mathematical reasoning capabilities of large language models. Recen
arXiv:2610.01936v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and th
arXiv:2610.00940v1 Announce Type: cross Abstract: We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questi
arXiv:2610.02191v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess th
arXiv:2609.39066v1 Announce Type: new Abstract: Conventional image forgery detection methods produce binary scores or pixel-level masks without interpretable evidence, while recent multimodal large la
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving
arXiv:2609.38924v1 Announce Type: new Abstract: Major adverse cardiovascular events (MACE) remain the leading cause of mortality worldwide. Opportunistic screening using routinely acquired clinical da
arXiv:2609.38332v1 Announce Type: cross Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context
arXiv:2609.39490v1 Announce Type: cross Abstract: Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and
arXiv:2609.38672v1 Announce Type: cross Abstract: Beam-search-based test-time methods provide an effective way to improve large language model (LLM) performance on long-horizon generation by pruning i
arXiv:2609.39967v1 Announce Type: cross Abstract: Recursive reasoning models apply a small shared Transformer block many times to refine a latent state. This gives them large effective depth with few
arXiv:2609.36461v1 Announce Type: new Abstract: Large language models often improve problem-solving performance by generating multi-step reasoning paths, yet how to analyze the hidden states along the
arXiv:2609.34124v1 Announce Type: new Abstract: Cross-view spatial reasoning requires a model to align different viewpoints into a coherent spatial representation, yet this ability remains challenging
arXiv:2609.34826v1 Announce Type: new Abstract: Humans often solve spatial problems by mentally simulating visual transformations. In contrast, conventional vision-language models (VLMs) reason primar
arXiv:2602.01034v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-langu
arXiv:2609.27340v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as natural-language interfaces for robotic systems, yet their integration with Robot Operating System
arXiv:2609.28272v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mecha
arXiv:2508.13680v5 Announce Type: replace Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) in
arXiv:2609.25841v1 Announce Type: new Abstract: Metric reasoning is a critical and challenging task for Vision Language Models (VLMs), playing a pivotal role in embodied AI tasks such as robotic manip
arXiv:2609.24066v1 Announce Type: new Abstract: Best-of-N is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and hig
arXiv:2609.24480v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the conve
arXiv:2609.20849v1 Announce Type: new Abstract: Large Audio Language Models (LALMs) perform well on complex question answering but often show a reasoning gap, where explicit Chain-of-Thought (CoT) red
I said 'auto-regressive LLMs, in and of themselves, will not lead human-level AI' That statement is still totally true. First, the reasoning abilities of current AI systems are based non-auto-regressi
arXiv:2609.19156v1 Announce Type: new Abstract: Data-driven fine-tuning is widely adopted to enhance reasoning in Large Language Models (LLMs) due to its simplicity and efficiency. However, mainstream
arXiv:2609.19671v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and un
arXiv:2609.18597v1 Announce Type: new Abstract: Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily rely on supervised GNN-based models, which re
arXiv:2603.12264v2 Announce Type: replace Abstract: Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natura
arXiv:2609.16012v1 Announce Type: new Abstract: Despite significant progress in general visual question answering and cross-modal understanding, multimodal large language models still face a pronounce
arXiv:2609.16372v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across g
arXiv:2609.16660v1 Announce Type: new Abstract: Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathemat