Daily Paper Cast

• LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

  🤗 Upvotes: 140 | cs.CV Authors: Zuhao Yang, Sudong Wang, Kaichen Zhang, Keming Wu, Sicong Leng, Yifan Zhang, Chengwei Qin, Shijian Lu, Xingxuan Li, Lidong Bing Title: LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling Arxiv: http://arxiv.org/abs/2511.20785v1 Abstract: Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and temporally dispersed. Inspired by how humans comprehend long videos - by first skimming globally and then examining relevant clips for details - we introduce LongVT, an end-to-end agentic framework that enables "Thinking with Long Videos" via interleaved Multimodal Chain-of-Tool-Thought. Specifically, we exploit LMMs' inherent temporal grounding ability as a native video cropping tool to zoom in on a specific video clip and resample finer-grained video frames. This global-to-local reasoning loop continues until answers are grounded in retrieved visual evidence. Given the scarcity of fine-grained question-answering (QA) data for the long video reasoning task, we curate and will release a data suite named VideoSIAH to facilitate both training and evaluation. Specifically, our training dataset consists of 247.9K samples for tool-integrated cold-start supervised fine-tuning, 1.6K samples for agentic reinforcement learning, and 15.4K samples for agentic reinforcement fine-tuning, respectively. Our evaluation benchmark consists of 1,280 QA pairs that are carefully curated through a semi-automatic data pipeline with human-in-the-loop validation. With a meticulously designed three-stage training strategy and extensive empirical validation, LongVT consistently outperforms existing strong baselines across four challenging long-video understanding and reasoning benchmarks. Our codes, data, and model checkpoints are publicly available at https://github.com/EvolvingLMMs-Lab/LongVT .

  --------  

  23:00

  --------

  23:00
• Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

  🤗 Upvotes: 83 | cs.CV, cs.AI Authors: Juanxi Tian, Siyuan Li, Conghui He, Lijun Wu, Cheng Tan Title: Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights Arxiv: http://arxiv.org/abs/2512.01816v1 Abstract: Current multimodal models aim to transcend the limitations of single-modality representations by unifying understanding and generation, often using text-to-image (T2I) tasks to calibrate semantic consistency. However, their reliance on static, single-image generation in training and evaluation leads to overfitting to static pattern matching and semantic fusion, while fundamentally hindering their ability to model dynamic processes that unfold over time. To address these constraints, we propose Envision-a causal event progression benchmark for chained text-to-multi-image generation. Grounded in world knowledge and structured by spatiotemporal causality, it reorganizes existing evaluation dimensions and includes 1,000 four-stage prompts spanning six scientific and humanities domains. To transition evaluation from single images to sequential frames and assess whether models truly internalize world knowledge while adhering to causal-temporal constraints, we introduce Envision-Score, a holistic metric integrating multi-dimensional consistency, physicality, and aesthetics. Comprehensive evaluation of 15 models (10 specialized T2I models, 5 unified models) uncovers: specialized T2I models demonstrate proficiency in aesthetic rendering yet lack intrinsic world knowledge. Unified multimodal models bridge this gap, consistently outperforming specialized counterparts in causal narrative coherence. However, even these unified architectures remain subordinate to closed-source models and struggle to overcome the core challenge of spatiotemporal consistency. This demonstrates that a focus on causally-isolated single images impedes multi-frame reasoning and generation, promoting static pattern matching over dynamic world modeling-ultimately limiting world knowledge internalization, generation.

  --------  

  24:10

  --------

  24:10
• Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

  🤗 Upvotes: 56 | cs.LG, cs.AI, cs.CL Authors: Chujie Zheng, Kai Dang, Bowen Yu, Mingze Li, Huiqiang Jiang, Junrong Lin, Yuqiong Liu, Hao Lin, Chencan Wu, Feng Hu, An Yang, Jingren Zhou, Junyang Lin Title: Stabilizing Reinforcement Learning with LLMs: Formulation and Practices Arxiv: http://arxiv.org/abs/2512.01374v2 Abstract: This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy gradient methods such as REINFORCE. Specifically, through a first-order approximation, we show that this surrogate becomes increasingly valid only when both the training-inference discrepancy and policy staleness are minimized. This insight provides a principled explanation for the crucial role of several widely adopted techniques in stabilizing RL training, including importance sampling correction, clipping, and particularly Routing Replay for Mixture-of-Experts (MoE) models. Through extensive experiments with a 30B MoE model totaling hundreds of thousands of GPU hours, we show that for on-policy training, the basic policy gradient algorithm with importance sampling correction achieves the highest training stability. When off-policy updates are introduced to accelerate convergence, combining clipping and Routing Replay becomes essential to mitigate the instability caused by policy staleness. Notably, once training is stabilized, prolonged optimization consistently yields comparable final performance regardless of cold-start initialization. We hope that the shared insights and the developed recipes for stable RL training will facilitate future research.

  --------  

  19:41

  --------

  19:41
• How Far Are We from Genuinely Useful Deep Research Agents?

  🤗 Upvotes: 44 | cs.CL Authors: Dingling Zhang, He Zhu, Jincheng Ren, Kangqi Song, Xinran Zhou, Boyu Feng, Shudong Liu, Jiabin Luo, Weihao Xie, Zhaohui Wang, Tianrui Qin, King Zhu, Yuqing Wang, Qianben Chen, Yuchen Eleanor Jiang, Wei Wang, Jiaheng Liu, Wangchunshu Zhou Title: How Far Are We from Genuinely Useful Deep Research Agents? Arxiv: http://arxiv.org/abs/2512.01948v1 Abstract: Deep Research Agents (DRAs) aim to automatically produce analyst-level reports through iterative information retrieval and synthesis. However, most existing DRAs were validated on question-answering benchmarks, while research on generating comprehensive reports remains overlooked. Worse, current benchmarks for report synthesis suffer from task complexity and subjective metrics -- this fails to reflect user demands and limits the practical utility of generated reports. To address these gaps, we present Fine-grained DEepResearch bench (FINDER), an enhanced benchmark consisting of 100 human-curated research tasks with 419 structured checklist items that standardize report structure, analytical depth, and factual grounding. Based on approximately 1,000 reports produced by mainstream DRAs, we further propose Deep rEsearch Failure Taxonomy (DEFT), the first failure taxonomy for deep research agents. DEFT contains 14 fine-grained failure modes across reasoning, retrieval, and generation, and is built upon grounded theory with human-LLM co-annotating and inter-annotator reliability validation. Our experimental findings reveal that current DRAs struggle not with task comprehension but with evidence integration, verification, and reasoning-resilient planning.

  --------  

  24:37

  --------

  24:37
• What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

  🤗 Upvotes: 41 | cs.CV Authors: Minh-Quan Le, Yuanzhi Zhu, Vicky Kalogeiton, Dimitris Samaras Title: What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards Arxiv: http://arxiv.org/abs/2512.00425v1 Abstract: Recent video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistently-revealing a persistent gap between visual realism and physical realism. We propose $\texttt{NewtonRewards}$, the first physics-grounded post-training framework for video generation based on $\textit{verifiable rewards}$. Instead of relying on human or VLM feedback, $\texttt{NewtonRewards}$ extracts $\textit{measurable proxies}$ from generated videos using frozen utility models: optical flow serves as a proxy for velocity, while high-level appearance features serve as a proxy for mass. These proxies enable explicit enforcement of Newtonian structure through two complementary rewards: a Newtonian kinematic constraint enforcing constant-acceleration dynamics, and a mass conservation reward preventing trivial, degenerate solutions. We evaluate $\texttt{NewtonRewards}$ on five Newtonian Motion Primitives (free fall, horizontal/parabolic throw, and ramp sliding down/up) using our newly constructed large-scale benchmark, $\texttt{NewtonBench-60K}$. Across all primitives in visual and physics metrics, $\texttt{NewtonRewards}$ consistently improves physical plausibility, motion smoothness, and temporal coherence over prior post-training methods. It further maintains strong performance under out-of-distribution shifts in height, speed, and friction. Our results show that physics-grounded verifiable rewards offer a scalable path toward physics-aware video generation.

  --------  

  22:15

  --------

  22:15

Meer Wetenschap podcasts

Trending Wetenschap -podcasts

Over Daily Paper Cast