Knowledge catalogue
arXiv:2609.29940v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on
arXiv:2609.27374v1 Announce Type: cross Abstract: Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks. The predominant approach, repeated s
arXiv:2609.25356v1 Announce Type: new Abstract: Large language models (LLMs) offer great potential to automate a broad range of telecom engineering tasks by reasoning over standards, network configura
arXiv:2609.23726v1 Announce Type: new Abstract: Large language models have shown strong performance across a range of legal tasks, but existing benchmarks rarely evaluate the ability to take and defen
arXiv:2609.24196v1 Announce Type: new Abstract: Looped Language Models (LoopLMs) perform 'latent reasoning' by recursively refining internal latent representations with shared weights, offering a more
arXiv:2605.13165v2 Announce Type: replace Abstract: Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is espec
arXiv:2609.21492v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has been shown to improve the performance of large language models (LLMs), yet existing optimization methods largely re
arXiv:2609.18471v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often degrades when handling harmful queries. Existin
arXiv:2503.10265v3 Announce Type: replace Abstract: Robotic-assisted surgery (RAS) is central to modern surgery, driving the need for intelligent systems with accurate scene understanding. Most existi
arXiv:2609.13152v1 Announce Type: new Abstract: Large language models (LLMs) perform strongly on static science benchmarks, yet their ability to reason about the physical world through active experime
arXiv:2509.18930v4 Announce Type: replace-cross Abstract: Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning. Despite its
arXiv:2609.13158v1 Announce Type: new Abstract: Large Vision--Language Models (LVLMs) are increasingly expected to perform visual question answering (VQA) over planar media. However, existing planar V
arXiv:2609.13770v1 Announce Type: cross Abstract: Specialist distillation effectively transfers domain expertise to student models via teacher-generated reasoning trajectories. However, when these spe
arXiv:2504.07825v2 Announce Type: replace Abstract: Commonsense reasoning is a key language model capability, as it is purportedly a prerequisite for many basic tasks, unlike specific factual knowledg
arXiv:2609.10815v1 Announce Type: cross Abstract: Police body-worn camera (BWC) footage has emerged as a critical aspect of law enforcement that ensures legal transparency, officer accountability, and
arXiv:2609.09928v1 Announce Type: new Abstract: Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact cont
arXiv:2602.06034v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improv
arXiv:2603.16112v2 Announce Type: replace-cross Abstract: Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked e
arXiv:2609.07036v1 Announce Type: cross Abstract: We identify the Flow Moment, a reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the r
arXiv:2603.25565v2 Announce Type: replace Abstract: Current Large Multimodal Models (LMMs) in Earth observation are predominantly evaluated on planar optical tasks and often neglect the vertical dimen
arXiv:2609.08867v1 Announce Type: new Abstract: Reasoning segmentation converts an implicit linguistic conclusion into a precise mask, requiring both semantic identification and spatial grounding. Exi
arXiv:2609.04782v1 Announce Type: new Abstract: Autoregressive (AR) large language models formulate reasoning as token-level probabilistic sampling, which induces three fundamental defects in complex
arXiv:2609.04565v1 Announce Type: new Abstract: Large language models demonstrate increasingly strong reasoning capabilities through effective post-training. Yet, prevailing post-training methods opti
Reasoning from scratch round 2: In this video, I cover the text generation process in LLMs and KV caching (to prepare the base model before adding reasoning techniques in the upcoming ones). 00:00 Int
arXiv:2609.02702v1 Announce Type: new Abstract: Transformers process information causally, but long-context reasoning may depend on task state discovered only later. We formalize this mismatch through
Hey everyone, Wanted to share a short paper we just published exploring a simple but surprisingly effective optimization for sparse MoE reasoning models. The problem: MoE reasoning models (especially
arXiv:2601.06853v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting is widely adopted for mathematical problem solving, including in low-resource languages, yet its behavior under irr
arXiv:2609.00738v1 Announce Type: new Abstract: Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving
arXiv:2609.00879v1 Announce Type: new Abstract: Reliable disaster damage assessment requires models that provide both accurate predictions and transparent explanations. However, existing multimodal ap
arXiv:2608.28771v1 Announce Type: new Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with
arXiv:2608.29835v1 Announce Type: new Abstract: Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central f
arXiv:2608.29616v1 Announce Type: new Abstract: Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classificati
arXiv:2507.06415v3 Announce Type: replace Abstract: Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. In this work, we propose PERK (Param
arXiv:2505.03654v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models have shown strong performance across multimodal tasks, and recent personalized MLLMs can recognize user-speci
arXiv:2608.28701v1 Announce Type: new Abstract: Diagram-to-graph topology extraction aims to extract a graph of entities and their connections from a structural diagram. This task remains challenging
arXiv:2608.27549v1 Announce Type: new Abstract: Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can r
arXiv:2608.27461v1 Announce Type: new Abstract: Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ab
arXiv:2601.13029v4 Announce Type: replace Abstract: While Vision-Language Models (VLMs) excel at 2D visual understanding, they remain constrained by 2D-centric paradigm that severely limits genuine 3D
arXiv:2608.24310v1 Announce Type: new Abstract: Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction,
arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reasoni
arXiv:2608.20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether
arXiv:2608.16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual informa
arXiv:2608.15392v1 Announce Type: new Abstract: Chain-of-thought monitoring is a potentially useful safety signal, but its reliability across languages and behavioral settings remains uncertain. In a
arXiv:2604.01413v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG)
arXiv:2608.13588v1 Announce Type: cross Abstract: Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation syste
iq2_xxs tensor level allocation recovered reasoning from 28.9 -> 69.5 at the same 3.3gb budget. https://huggingface.co/ByteOtter/gemma-4-E4B-it-CADA-IQ2_XXS I posted my Gemma 4 12B q3 result a couple
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, fin
arXiv:2608.12920v1 Announce Type: new Abstract: Sports-video understanding is moving beyond event recognition toward explaining how actions collectively shape match progression, however, existing tenn
arXiv:2608.12220v1 Announce Type: cross Abstract: Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to c
arXiv:2608.10492v1 Announce Type: new Abstract: Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, w
arXiv:2608.07742v1 Announce Type: new Abstract: Visual-language models (VLMs) frequently struggle with robustness issues in real-world situations due to low- or varying-quality input images. In this p
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:2608.08786v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers ar
arXiv:2608.06938v1 Announce Type: cross Abstract: The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reas
arXiv:2608.01980v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning can improve performance on difficult video questions but often wastes decoding tokens on simple ones. We study whether
arXiv:2608.00743v1 Announce Type: new Abstract: Multimodal large language models have advanced visual understanding, yet perception-intensive reasoning remains challenging. Recent latent visual reason
arXiv:2608.01347v1 Announce Type: new Abstract: Large reasoning models used as coding agents incur costs from deliberation, tool calls, and repeated agent turns, yet the causal effect of prompt wordin
arXiv:2607.29185v1 Announce Type: new Abstract: Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs ena
arXiv:2607.29586v1 Announce Type: cross Abstract: The Abstraction and Reasoning Corpus (ARC) tests whether a model can infer an unseen transformation from a few input-output examples and apply it to a
arXiv:2607.25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or b