Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in textual and 2D visual reasoning, yet their ability to understand and reason over 3D data remains limited. The issues become more challenging for understanding standalone 3D point cloud due to the high interclass confusion. In this work, we propose Point-Graph LLM (PGLLM), a framework that enables more effective 3D point cloud understanding by integrating in-context prompting and score refinement at test-time, respecting supporting data manifold. Our method first employs a pre-trained point cloud encoder which are used to construct a graph where edges encode visual similarity. Each support point cloud sample is converted to a textual caption via pre-trained PointLLM. For a test query, the graph is used to retrieve relevant neighbors whose captions serve as contextual demonstrations for a second stage LLM for final reasoning, a process we term in-context guidance. Furthermore, we introduce a confidence score refinement mechanism based on label propagation to enhance the reliability of LLM predictions for classification and out-of-distribution (OOD) detection tasks. All the above optimizations are carried out fully at test-time. Extensive experiments across diverse 3D datasets and tasks demonstrate that PGLLM consistently improves accuracy and robustness over prior baselines with very almost no additional computation cost, showcasing a promising direction toward native 3D reasoning with MLLMs.
论文检索
输入标题、作者或关键词，从 12,113 篇学术成果中精准定位
Vision foundation models are typically trained as static feature extractors, forcing the burden of task adaptation onto large downstream models. We propose a different paradigm: instead of solely feeding visual features into language, we use language itself to dynamically guide the vision encoder. Our method, Language-Instructed Vision Embeddings (LIVE), leverages language as high-level guidance to produce task-centric embeddings at inference time—without requiring task-specific retraining. This enables the encoder to focus attention on contextually relevant aspects of the input, yielding more controllable and generalizable representations. Empirically, LIVE reduces visual hallucinations (+34 points on MMVP), outperforms vision–language models with orders of magnitude more parameters on visual question answering, and generalizes to unseen instructions and tasks---offering a direct path toward adaptive, instruction-driven visual intelligence.
Oversmoothing is a fundamental challenge in graph neural networks (GNNs): as the number of layers increases, node embeddings become increasingly similar, and model performance drops sharply. Traditionally, oversmoothing has been quantified using metrics that measure the similarity of neighbouring node features, such as the Dirichlet energy. We argue that these metrics have critical limitations and fail to reliably capture oversmoothing in realistic scenarios. For instance, they provide meaningful insights only for very deep networks, while typical GNNs show a performance drop already with as few as 10 layers. As an alternative, we propose measuring oversmoothing by examining the numerical or effective rank of the feature representations. We provide extensive numerical evaluation across diverse graph architectures and datasets to show that rank-based metrics consistently capture oversmoothing, whereas energy-based metrics often fail. Notably, we reveal that drops in the rank align closely with performance degradation, even in scenarios where energy metrics remain unchanged. Along with the experimental evaluation, we provide theoretical support for this approach, clarifying why Dirichlet-like measures may fail to capture performance drop and proving that the numerical rank of feature representations collapses to one for a broad family of GNN architectures.
Large Vision Language Models (LVLMs) have recently emerged as powerful architectures capable of understanding and reasoning over both visual and textual information. These models typically rely on two key components: a Vision Transformer (ViT) and a Large Language Model (LLM). ViT encodes visual content into a sequence of image tokens and serves as the perceptual front-end -- the eyes of the model. In contrast, the LLM interprets these tokens to perform high-level reasoning, generates responses, and functions as the cognitive core -- the brain of the model. However, it remains unclear which visual tokens contribute most significantly to understanding and reasoning, and how effectively these signals are propagated from ViT to the LLM. While most existing works have focused on identifying attention sinks, low-semantic tokens receiving disproportionately high attention, within the LLM, we shift the focus to the vision encoder by identifying a class of high-norm visual tokens from ViT, referred to as ViT attention sinks -- a problem that has been rarely studied but is indeed very important for LVLMs. Our findings show that these ViT sinks encapsulate high-level semantic concepts from images, allowing the LLM to perform more effective understanding and reasoning. Despite their importance, these sink tokens are often overlooked in existing LVLM architectures. To explore their contribution, we present both qualitative and quantitative analyses of the information embedded in these sink tokens. We also propose both training-free and training-based approaches to better leverage how this information is interpreted by the LLM, and to what extent. By explicitly utilizing these tokens, we demonstrate substantial improvements across a range of LVLMs and visual reasoning tasks, including but not limited to mathematical problem solving, logical inference, and geometric understanding, highlighting the untapped potential of ViT attention sinks in enhancing visual reasoning.
Instruction fine-tuning is a key technique for enhancing the performance of large language models (LLMs), but low-quality and redundant data often hinder its effectiveness. Recent studies suggest that filtering a small amount of high-quality data for instruction fine-tuning can achieve faster and more efficient training performance. However, existing data filtering approaches predominantly depend on predefined evaluation models or manually designed metrics, without leveraging information from the target LLM itself. This limitation may result in a mismatch between the filtering criteria and the actual requirements of the LLM being fine-tuned, thereby reducing the effectiveness of the fine-tuning process. To address these issues, we propose a novel perspective: the hidden states of LLMs implicitly reflect the quality of the training data. Based on this insight, we propose a novel data filtering method that extracts the hidden states that reflect the target LLM’s perception of the data as representative features, and builds a data classification model upon them, which outputs the Contrastive Perception Quality Score (CPQS) for dataset filtering. Our experiments are conducted in both general and downstream domains. (1) In the general domain, our experiments show that training on under 10\% of the data from both the Alpaca\_GPT4 and DeepSeek-R1 synthesized reasoning datasets enables our method to outperform models trained on the complete datasets. Moreover, it surpasses the performance of current state-of-the-art data-selection techniques. (2) In downstream tasks, our approach delivers an average performance gain exceeding 3.6\% over leading data-selection algorithms across multiple benchmarks, including GSM8K, HumanEval, and HumanEval-Plus.
Vector quantization, a problem rooted in Shannon's source coding theory, aims to quantize high-dimensional Euclidean vectors while minimizing distortion in their geometric structure. We propose TurboQuant to address both mean-squared error (MSE) and inner product distortion, overcoming limitations of existing methods that fail to achieve optimal distortion rates. Our data-oblivious algorithms, suitable for online applications, achieve near-optimal distortion rates (within a small constant factor) across all bit-widths and dimensions. TurboQuant achieves this by randomly rotating input vectors, inducing a concentrated Beta distribution on coordinates, and leveraging the near-independence property of distinct coordinates in high dimensions to simply apply optimal scalar quantizers per each coordinate. Recognizing that MSE-optimal quantizers introduce bias in inner product estimation, we propose a two-stage approach: applying an MSE quantizer followed by a 1-bit Quantized JL (QJL) transform on the residual, resulting in an unbiased inner product quantizer. We also provide a formal proof of the information-theoretic lower bounds on best achievable distortion rate by any vector quantizer, demonstrating that TurboQuant closely matches these bounds, differing only by a small constant ($\approx 2.7$) factor. Experimental results validate our theoretical findings, showing that for KV cache quantization, we achieve absolute quality neutrality with 3.5 bits per channel and marginal quality degradation with 2.5 bits per channel. Furthermore, in nearest neighbor search tasks, our method outperforms existing product quantization techniques in recall while reducing indexing time to virtually zero.
Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-10M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we load this trained KV cache, which we call a Cartridge, and decode a response. Critically, the cost of training a Cartridge can be amortized across all the queries referencing the same corpus. However, we find that the naive approach of training the Cartridge with next-token prediction on the corpus is not competitive with ICL. Instead, we propose self-study, a training recipe in which we generate synthetic conversations about the corpus and train the Cartridge with a context-distillation objective. We find that Cartridges trained with self-study replicate the functionality of ICL, while being significantly cheaper to serve. On challenging long-context benchmarks, Cartridges trained with self-study match ICL performance while using 38.6x less memory and enabling 26.4x higher throughput. Self-study also extends the model's effective context length (e.g. from 128k to 484k tokens on MTOB) and surprisingly, leads to Cartridges that can be composed at inference time without retraining.
Recent incidents have revealed that large language models (LLMs) deployed in mental health contexts can generate unsafe guidance, including reports of chatbots encouraging self-harm. Such risks highlight the urgent need for rigorous, clinically valid evaluation before integration into care. However, existing benchmarks remain inadequate: 1) they rely on synthetic or weakly validated data, undermining clinical reliability; 2) they reduce counseling to isolated QA or single-turn tasks, overlooking the extended, adaptive nature of real interactions; and 3) they rarely capture the formal therapeutic structure of sessions. These gaps risk overestimating LLM competence and obscuring safety-critical failures. To address this, we present \textbf{CareBench-CBT}, the largest clinically validated benchmark for CBT-based counseling, unifying thousands of expert-curated items, realistic multi-turn dialogues, and formal CBT structural alignment. Evaluating 18 state-of-the-art LLMs reveals consistent gaps: high scores on public QA degrade under expert rephrasing, vignette reasoning remains difficult, and dialogue competence falls well below human counselors. Recognizing that long-horizon context management limits multi-turn performance, we further propose Hierarchical Therapy Memory (HTM), a training-free inference framework that structures dialogue history into global states and episodic summaries. HTM consistently improves session-level therapeutic coherence while reducing computational latency. Together, CareBench-CBT and HTM provide a rigorous foundation for advancing the safe and responsible integration of LLMs into mental health care. All code and data are released in the Supplementary Materials.
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind autoregressive models due to the lack of Key-Value (KV) Cache and quality degradation when decoding multiple tokens simultaneously. To bridge this gap, we introduce Fast-dLLM, a method that incorporates a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop. Additionally, we identify the root cause of generation quality degradation in parallel decoding as the disruption of token dependencies under the conditional independence assumption. To address this, Fast-dLLM also proposes a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality. Experimental results on LLaDA and Dream models across multiple LLM benchmarks demonstrate up to 27.6× throughput improvement with minimal accuracy loss, closing the performance gap with autoregressive models and paving the way for practical deployment of Diffusion LLMs.
Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planning and iterative refinement features of dLLMs are particularly useful for code generation. However, current training and inference mechanisms for dLLMs in coding are still under-explored. To demystify the decoding behavior of dLLMs and unlock their potential for coding, we systematically investigate their denoising processes and reinforcement learning (RL) methods. We train a 7B dLLM, DiffuCoder, on 130B tokens of code. Using this model as a testbed, we analyze its decoding behavior, revealing how it differs from that of AR models: (1) dLLMs can decide how causal their generation should be without relying on semi-AR decoding, and (2) increasing the sampling temperature diversifies not only token choices but also their generation order. This diversity creates a rich search space for RL rollouts. For RL training, to reduce the variance of token log-likelihood estimates and maintain training efficiency, we propose coupled-GRPO, a novel sampling scheme that constructs complementary mask noise for completions used in training. In our experiments, coupled-GRPO significantly improves DiffuCoder's performance on code generation benchmarks (+4.4\% on EvalPlus) and reduces reliance on AR bias during decoding. Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework.
Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. We conduct a systematic analysis across models and datasets and discover a U-shaped entropy pattern: high entropy on simple problems despite high accuracy, low entropy on medium difficulty, and high entropy on hard problems reflecting uncertainty. The 22--25\% entropy reduction from simple to optimal regions reveals a fundamental inefficiency—an \emph{overthinking} phenomenon on easy instances. Building on these insights, we introduce \textbf{DiffAdapt}, a lightweight, deployment-ready framework that predicts problem difficulty from hidden states and selects among Easy/Normal/Hard reasoning strategies to allocate computation adaptively. DiffAdapt requires no retraining of the base LLM and is compatible with common inference optimizations. Across five models and eight benchmarks, DiffAdapt achieves comparable or improved accuracy while reducing token usage by up to 22.4\%, establishing a practical path toward compute-efficient reasoning.
Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of approaches paradoxically require a diffusion model pre-trained on the full target dataset, undermining the very purpose of DD and incurring prohibitive training costs. Second, although some methods turn to general text-to-image models without relying on such target-specific training, they suffer from a significant distributional mismatch, as the web-scale priors encapsulated in these foundation models fail to faithfully capture the target-specific semantics, leading to suboptimal performance. To tackle these challenges, we propose Core Distribution Alignment (CoDA), a framework that enables effective DD using only an off-the-shelf text-to-image model. Our key idea is to first identify the ``intrinsic core distribution'' of the target dataset using a robust density-based discovery mechanism. We then steer the generative process to align the generated samples with this core distribution. By doing so, CoDA effectively bridges the gap between general-purpose generative priors and target semantics, yielding highly representative distilled datasets. Extensive experiments suggest that, without relying on a generative model specifically trained on the target dataset, CoDA achieves performance on par with or even superior to previous methods with such reliance across all benchmarks, including ImageNet-1K and its subsets. Notably, it establishes a new state-of-the-art accuracy of 60.4\% at the 50-images-per-class (IPC) setup on ImageNet-1K. Our code is available on the project webpage: https://github.com/zzzlt422/CoDA
Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based optimization. We observe that the key impediment to effective GRPO training of flow models is the temporal uniformity assumption in existing approaches: sparse terminal rewards with uniform credit assignment fail to capture the varying criticality of decisions across generation timesteps, resulting in inefficient exploration and suboptimal convergence. To remedy this shortcoming, we introduce TempFlow-GRPO (Temporal Flow-GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation. TempFlow-GRPO introduces three key innovations: (i) a trajectory branching mechanism that provides process rewards by concentrating stochasticity at designated branching points, enabling precise credit assignment without requiring specialized intermediate reward models; (ii) a noise-aware weighting scheme that modulates policy optimization according to the intrinsic exploration potential of each timestep, prioritizing learning during high-impact early stages while ensuring stable refinement in later phases; and (iii) a seed group strategy that controls for initialization effects to isolate exploration contributions. These innovations endow the model with temporally-aware optimization that respects the underlying generative dynamics, leading to state-of-the-art performance in human preference alignment and text-to-image benchmarks.
Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding proving ground: analysts routinely conduct complex, multi-step searches over time-sensitive, domain-specific data, making it ideal for assessing both search proficiency and knowledge-grounded reasoning. Yet no existing open financial datasets evaluate data searching capability of end-to-end agents, largely because constructing realistic, complicated tasks requires deep financial expertise and time-sensitive data is hard to evaluate. We present FinSearchComp, the first fully open-source agent benchmark for realistic, open-domain financial search and reasoning. FinSearchComp comprises three tasks, Time-Sensitive Data Fetching, Simple Historical Lookup, and Complex Historical Investigation, closely reproducing real-world financial analyst workflows. To ensure difficulty and reliability, we engage $70$ professional financial experts for annotation and implement a rigorous multi-stage quality-assurance pipeline. The benchmark includes $635$ questions spanning global and Greater China markets, and we evaluate $21$ models (products) on it. Grok 4 (web) tops the global subset, approaching expert-level accuracy. DouBao (web) leads on the Greater China subset. Experimental analyses show that equipping agents with web search and financial plugins substantially improves results on FinSearchComp, and the country origin of models and tools impact performance significantly. By aligning with realistic analyst tasks and providing end-to-end evaluation, FinSearchComp offers a professional, high-difficulty testbed for complex financial search and reasoning.
Reinforcement Learning with Verifiable Rewards (RLVR) for large language models (LLMs) has achieved remarkable progress in enhancing LLMs’ reasoning capabilities on tasks with clear correctness criteria, such as mathematical reasoning tasks. Several training metrics, such as entropy or response length, have been observed to correlate with different reasoning behaviors in reinforcement learning. Prior approaches incorporate such priors through reward or advantage shaping, which often relies on hand-crafted penalties and preferences (e.g., higher-is-better or lower-is-better). However, without careful hyper-parameter tuning, these directional priors can be overly biased and may lead to failure. To this end, we introduce ***C****onditional adv****AN****tage estimati****ON*** (***CANON***), amplifying the impact of the target metric without presuming its direction. Specifically, *CANON* regroups the sampled responses into two groups based on the higher or lower value of a target metric, measures which metric trend contributes to better performance through inter-group comparison, and identifies the better response within the same group. In summary, *CANON* based on entropy consistently outperforms prior methods across three LLMs on both math reasoning and high-complexity logic tasks. When applied to response length, *CANON* further improves token efficiency, yielding a more favorable Pareto frontier in the performance–cost trade-off.
Optimization · Large Scale, Parallel and Distributed
Training billion-parameter Transformers is often brittle, with transient loss spikes and divergence that waste compute. Even though the recently developed Edge of Stability (EoS) theory provides a powerful tool to understand and control the stability of optimization methods via the (preconditioned) curvature, these curvature-controlling methods are not popular in large-scale Transformer training due to the complexity of curvature estimation. To this end, we first introduce a fast online estimator of the largest (preconditioned) Hessian eigenvalue (i.e., curvature) based on a warm-started variant for power iteration with Hessian–vector products. We show theoretically, and verify empirically, that the proposed method makes per-iteration curvature tracking feasible at billion-parameter scale while being more accurate. Using this tool, we find that training instabilities coincide with surges in preconditioned curvature and that curvature grows with depth. Motivated by these observations, we propose architecture warm-up: progressively growing network depth to carefully control the preconditioned Hessian and stabilize training. Experiments on large Transformers validate that our approach enables efficient curvature tracking and reduces instabilities compared to existing state-of-the-art stabilization techniques without slowing down convergence.
Large Language Models (LLMs) can enhance their reasoning by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn settings using Reinforcement Learning (RL) often exhibits training instability and degraded performance. We attribute the instability to harmful negative samples resulting from distributional drift and compounding errors induced by using external tool outputs during multi-turn rollout. To address this issue, we introduce SimpleTIR, a simple method that stabilizes multi-turn TIR training via filtering out trajectories with "void turns", i.e., turns that yield neither a code block nor a final answer. Specifically, we remove those trajectories from the policy update to block harmful gradients, while retaining them in advantage estimation to keep the estimate unbiased. Extensive experiments show that SimpleTIR effectively mitigates gradient norm explosion and stabilizes multi-turn RL training from base models. It achieves state-of-the-art performance on challenging math reasoning benchmarks, including an AIME24 score of 50.5 starting from the Qwen2.5-7B base model. SimpleTIR also promotes more diverse reasoning behaviors such as self-correction and cross-validation, outperforming prior methods trained from stronger instruction-tuned models.
The paradigm shift in large language models (LLMs) from instinctive responses to chain-of-thought (CoT) reasoning has fueled two prevailing assumptions: (1) reasoning capabilities only emerge in sufficiently large models, and (2) such capabilities require training on massive datasets. While the first assumption has already been challenged by recent sub-billion-parameter reasoning models such as Qwen3-0.6B and DeepSeek distilled variants, the second remains largely unquestioned. In this work, we revisit the necessity of scaling to extremely large corpora (>10T tokens) for reasoning emergence. By carefully curating and resampling open-source datasets that we identify as beneficial under our designed metrics, we demonstrate that strong reasoning abilities can emerge with far less data. Specifically, we show that only ~2T tokens of high-quality data are sufficient, and pre-training with 4.2T tokens on the dataset resampled from these ~2T tokens, followed by a established post-training procedure, enables the development of MobileLLM-R1, a series of sub-billion-parameter reasoning models that substantially outperform prior models trained on fully open-sourced data. For example, MobileLLM-R1-950M achieves an AIME score of 15.5, compared to just 0.6 for OLMo-2-1.48B and 0.3 for SmolLM-2-1.7B. Remarkably, despite being trained on only 11.7% of the tokens compared to Qwen3’s proprietary 36T-token corpus for pretraining, MobileLLM-R1-950M matches or surpasses Qwen3-0.6B across multiple reasoning benchmarks. To facilitate further research in this direction, we have made the models (https://huggingface.co/collections/facebook/mobilellm-r1) and code (https://github.com/facebookresearch/MobileLLM-R1) publicly available, along with the complete training recipe, data sources, and data mixing ratios.
Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on. Despite its advances, handling long videos remains challenging due to the difficulty in efficiently understanding the extremely long video context. This paper aims to address this issue from aspects of the model architecture, training data, training strategy, and evaluation benchmark. First, we propose a novel Hierarchical video token Compression (HiCo) method, which leverages visual redundancy in long videos to compress long video context from Clip-level to Video-level, reducing the computation significantly while preserving essential details, achieving an extreme compression ratio of approximately 1/50 with almost no performance loss. Second, we introduce a multi-stage short-to-long learning scheme, a large-scale dataset of real-world long videos named LongVid, and a challenging “Multi-Hop Needle-In- A-Video-Haystack” benchmark. Finally, we build a powerful video MLLM named VideoChat-Flash, which shows a leading performance on both mainstream long and short video benchmarks at the 2B and 7B model scales. It first gets 99.1% accuracy over 10,000 frames in NIAH among open-source models.
As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak attacks, with effectiveness varying across language contexts. This paper investigates the role of classical Chinese in jailbreak attacks. Owing to its conciseness and obscurity, classical Chinese can partially bypass existing safety constraints, exposing notable vulnerabilities in LLMs. Based on this observation, this paper proposes a framework, CC-BOS, for the automatic generation of classical Chinese adversarial prompts based on multi-dimensional fruit fly optimization, facilitating efficient and automated jailbreak attacks in black-box settings. Prompts are encoded into eight policy dimensions—covering role, behavior, mechanism, metaphor, expression, knowledge, trigger pattern and context; and iteratively refined via smell search, visual search, and cauchy mutation. This design enables efficient exploration of the search space, thereby enhancing the effectiveness of black-box jailbreak attacks. To enhance readability and evaluation accuracy, we further design a classical Chinese to English translation module. Extensive experiments demonstrate that effectiveness of the proposed CC-BOS, consistently outperforming state-of-the-art jailbreak attack methods.