Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process. However, existing parallel reasoning approaches suffer from performance degradation compared to their sequential counterparts, and often rely on specialized inference engines. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that matches the accuracy of comparably sized sequential reasoning models while significantly reducing inference latency via three key innovations: 1) a two-stage parallel trajectory generator that produces high-quality parallel chain-of-thought data for supervised fine-tuning; 2) a trie-based rollout design that enables parallel reasoning on any off-the-shelf autoregressive inference engine; and 3) a parallelization-aware reinforcement learning framework that trains the model to balance reasoning accuracy with effective parallelization. Across six challenging math reasoning benchmarks, ThreadWeaver trained on top of Qwen3-8B achieves performance on par with cutting-edge sequential reasoning models (79.9% on AIME24 and 71.9% on average) while delivering up to 1.53x speedup in token latency, establishing a new Pareto frontier between accuracy and efficiency.
论文检索
输入标题、作者或关键词，从 13,033 篇学术成果中精准定位
Applications · Computer Vision
Diffusion models deliver state-of-the-art image quality but are expensive to deploy. Post-training quantization (PTQ) can shrink models and speed up inference, yet residual quantization errors distort the diffusion distribution (the timestep-wise marginal over $\vx_t$), degrading sample quality. We propose a distribution-preserving framework that absorbs quantization error into the generative process without changing architecture or adding steps. Deformable Noise Scheduler (DNS) reinterprets quantization as a principled timestep shift, mapping the quantized prediction distribution $\vx_t$ back onto the original diffusion distribution so that the target marginal is preserved. Unlike trajectory-preserving or noise-injection methods limited to stochastic samplers, our approach preserves the distribution under both stochastic and deterministic samplers and extends to flow-matching with Gaussian conditional paths. It is plug-and-play and complements existing PTQ schemes. Empirically, our method consistently enhances generation quality across diverse backbones and existing PTQ baselines. Notably, when further quantizing the FP16 LoRA branch of SVDQuant to enable fully integer inference, our approach effectively mitigates the performance drop, reducing FID from 27.16 to 26.22.
Deep Learning · Generative Models and Autoencoders
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a *high-variance regime* near the prior, where optimization is challenging, and 2) a *low-variance regime* near the data distribution, where conditional and marginal velocities nearly coincide. Leveraging this insight, we propose **Stable Velocity**, a unified framework that improves both training and sampling. For training, we introduce Stable Velocity Matching (StableVM), an unbiased variance-reduction objective, along with Variance-Aware Representation Alignment (VA-REPA), which adaptively strengthen auxiliary supervision in the *low-variance regime*. For inference, we show that dynamics in the *low-variance regime* admit closed-form simplifications, enabling Stable Velocity Sampling (StableVS), a finetuning-free acceleration. Extensive experiments on ImageNet $256\times256$ and large pretrained text-to-image and text-to-video models, including SD3.5, Flux, Qwen-Image, and Wan2.2, demonstrate consistent improvements in training efficiency and more than $2\times$ faster sampling within the *low-variance regime* without degrading sample quality.
Deep Reinforcement Learning agents are in- creasingly used in safety-critical domains but remain vulnerable to stealthy backdoor attacks. Existing outer-loop attacks face a trade-off be- tween perceptual stealth, poisoning efficiency, and value-function consistency, often making the at- tack ineffective or easily exposed. To address these challenges, we propose SpecDRL, a uni- fied framework that ❶ embeds triggers in the least sensitive subspaces of the state manifold via Subspace-Aware Injection, exploiting percep- tual blind spots, ❷ selects the most influential time steps for poisoning through Value-Guided Strategic Sampling based on Return-to-Go and Temporal-Difference error, and ❸ preserves re- ward integrity via Bellman-Consistent Dynamic Reward Poisoning, which analytically enforces ϵ- consistency of value functions and bounds global return deviations. Experiments across 12 Atari en- vironments demonstrate that SpecDRL achieves near-100% attack success, accelerates backdoor convergence, and maintains benign task perfor- mance.
General Machine Learning · Methodology
Trajectory Inference (TI) seeks to reconstruct latent dynamical processes from snapshot data, which consist of independent samples from time-indexed marginals of an underlying stochastic system. In applications such as single-cell genomics, destructive measurements preclude direct observation of trajectories, making the induced distribution over paths fundamentally ill-posed given finitely many marginals. However, despite extensive work on modeling approaches, little attention has been paid to evaluating the inferred object itself, namely, a probability measure over trajectories. Since path-space laws are not identifiable from snapshot data, evaluation protocols based on predictive accuracy at held-out marginals provide only limited information and fail to constrain trajectory-level behavior. We introduce a general framework for estimating the Kullback–Leibler divergence (KL) between probability measures on function space: we obtain a tractable estimator that can be approximated from data, is practical, and scales to realistic problem sizes (number and size of snapshot data). We apply this framework to a systematic empirical study of trajectory inference methods on synthetic and real datasets. We show that current evaluation metrics yield inconsistent assessments, whereas path-space KL provides a coherent comparison that reveals discrepancies in inferred dynamics, particularly in regions with sparse or missing data. These results support the use of functional KL as a principled criterion for evaluating TI methods under partial observability.
Although Multimodal Large Language Models have made remarkable progress, they still struggle with long-video understanding due to the massive memory footprint of KV Caches. Exsiting methods often resort to disjoint retrieval or attention-based static reduction to achieve compression. However, these methods disrupt temporal continuity and ignore the varying information density across network layers. In this work, we reveal that memory allocation should mirror layer-wise semantic density, rather than adhering to a uniform budget. To this end, we introduce EAKV, a training-free entropy-driven adaptive KV compression framework that leverages attention entropy to adaptively allocate compression budgets, selectively preserving critical tokens while distilling redundant contexts into compact contextual anchors, thereby achieving granular memory allocation proportional to semantic density. Extensive experiments on four benchmarks demonstrate that EAKV surpasses existing methods across varying model scales with improvements ranging from 1.5% to 4.8%.
Iterative generative policies, such as diffusion models and flow matching, offer superior expressivity for continuous control but complicate Maximum Entropy Reinforcement Learning because their action log-densities are not directly accessible. To address this, we propose \textbf{Field Least-Energy Actor-Critic (FLAC)}, a likelihood-free framework that regulates policy stochasticity by penalizing the kinetic energy of the velocity field. Our key insight is to formulate policy optimization as a Generalized Schr\"odinger Bridge (GSB) problem relative to a high-entropy reference process (e.g., uniform). Under this view, the maximum-entropy principle emerges naturally as staying close to a high-entropy reference while optimizing return, without requiring explicit action densities. In this framework, kinetic energy serves as a physically grounded proxy for divergence from the reference: minimizing path-space energy bounds the deviation of the induced terminal action distribution. Building on this view, we derive an energy-regularized policy iteration scheme and a practical off-policy algorithm that automatically tunes the kinetic energy via a Lagrangian dual mechanism. Empirically, FLAC achieves superior or comparable performance on high-dimensional benchmarks relative to strong baselines, while avoiding explicit density estimation.
General Machine Learning · Evaluation
Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. This position paper argues that the root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by assessor agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. This design separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and deployment; we provide recommended practices that allow both agent developers and benchmark designers to adopt AAA with minimal additional effort; and we show how this approach turns agent evaluation from ad-hoc integration work into a reusable, portable, and production-aligned process. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.
Social Aspects · Everything Else
Many failures of deployed machine learning systems stem not from insufficient accuracy, but from neglecting responsibility as a core design requirement. While responsibility principles are widely studied, they are often treated as post-hoc checks rather than as integral factors of system design. This framework has reinforced the perception that responsible practices inherently trade-off with model performance. In this position paper, we challenge that assumption and argue that responsibility and performance are not inherently at odds. We adopt a lifecycle-oriented perspective, identifying which responsible AI principles are most critical at each stage, from problem formulation and data curation to training, deployment, and monitoring. Drawing on real-world instances, we show how misaligned choices at specific stages can compound downstream risks and how alternative design choices could have mitigated these failures. We argue that responsible AI should be understood as a system design challenge rather than a constraint, and we offer operational guidance for integrating responsibility into mainstream machine learning workflows in a way that supports, rather than undermines, real-world performance.
Deep Learning · Large Language Models
4-bit quantization reduces the memory footprint and latency of large language model inference, but its aggressive precision reduction can severely degrade accuracy. Prior methods address this by decomposing each weight matrix into two components (e.g., via singular value decomposition) and quantizing them separately, assigning the bulk of values to a low-precision residual component while handling outliers with a high-precision low-rank component. However, such decompositions are designed to minimize the real-valued energy of the residual, rather than the post-quantization error of the residual and low-rank components. We propose TwinQuant, a 4-bit quantization framework that learns quantization-friendly decomposed subspaces and jointly reshapes both the low-rank and residual components. TwinQuant learns component-specific transformations via a joint optimization over the Stiefel and general linear manifolds, flattening their distributions and reducing dynamic-range imbalance. To enable efficient end-to-end execution, we further design a fused dual-component kernel that pipelines the two-stage low-rank computation on-chip and merges both components with a single epilogue, avoiding intermediate global-memory traffic. Across LLaMA3 and Qwen3 models, TwinQuant preserves near-FP16 accuracy and delivers up to $2.11\times$ end-to-end speedup over an FP16 baseline.
Applications · Everything Else
Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn restricted scenarios, failing to capture the capability boundaries exposed by real-world interactive scientific workflows. To address this, we introduce XDomainBench, a diagnostic benchmark for interactive interdisciplinary scientific reasoning. We formalize the composition order and mixture structure to enable systematic stress-testing from single-discipline to inter-disciplinary, comprising 8,598 interactive sessions across 20 domains and 4 task categories, with 8 realistic trajectory patterns covering difficulty and domain-mixture dynamics, simulating real AI4S scenarios. Large-scale evaluation of LLMs reveals a systematic reasoning collapse as composition order increases, stemming from two root causes: (i) direct difficulty increases induced by domain composition, and (ii) indirect interaction-amplified failures where trajectory patterns trigger error accumulation, reasoning breaks, and domain confusion, ultimately leading to session collapse.
Deep Learning · Large Language Models
Existing decoding-time safety interventions are often reactive, relying on local signals to correct unsafe outputs after they emerge. Under adversarial prompts that drive generation into recurring unsafe response, such local signals provide weak guidance for stable repair. As a result, rollback and post-hoc rewriting often trade-off response quality with recurrent violations. To address these limitations, we propose RBCBF, a rollback-based decoding-time framework that jointly selects intervention steps and performs distribution-level corrective control. Our key innovation is a risk-aggregation formulation that views terminal violations as the accumulated build-up of risk along the prefix. By selecting rollback steps from these decisive prefixes, RBCBF moves rollback targeting beyond heuristic cues and turns it into a trajectory-level decision. RBCBF then applies invasive corrective control to the next-token distribution under multiple rule constraints. Across jailbreak-style evaluations, RBCBF outperforms prior rollback methods and decoding-time baselines, reducing harmful responses and substantially lowering violation recurrence.
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key paradigm for unlocking complex reasoning in Large Language Models (LLMs), yet its potential in 3D scene understanding remains untapped. To bridge this gap, we present Reinforcement Fine-Tuning for Video-based 3D Scene Understanding (3D-RFT), the first framework to extend RLVR to 3D perception and reasoning. Our pipeline operates in two stages: activating 3D-aware Multi-modal Large Language Models (MLLMs) via Supervised Fine-Tuning (SFT), followed by reinforcement fine-tuning using Group Relative Policy Optimization (GRPO) with strictly verifiable reward functions. We design task-specific rewards—such as 3D IoU and F1-score—to provide deterministic signals for spatial alignment. Extensive experiments demonstrate that 3D-RFT achieves state-of-the-art performance on video-based 3D scene understanding benchmarks, significantly outperforming VG LLM-8B on detection and grounding tasks. Moreover, our model surpasses larger mainstream models on VSI-Bench, demonstrating the efficiency of verifiable reinforcement learning. We conclude by offering valuable insights into optimal training strategies .
Reinforcement Learning · Deep RL
Hierarchical decision-making frameworks are pivotal for addressing complex control tasks, enabling agents to decompose intricate problems into manageable subgoals. Despite their promise, existing hierarchical policies face critical limitations: (i) reinforcement learning (RL)-based methods struggle to guarantee strict constraint satisfaction, and (ii) optimal control (OC)-based approaches often rely on myopic and computationally prohibitive formulations. To reconcile these trade-offs, hierarchical RL-OC architectures have emerged as a promising paradigm. However, the formulation of the lower-level optimization within these frameworks remains underexplored, often relying on heuristic or myopic objectives. In this work, we propose a principled framework that systematically integrates upper-level goal abstraction with structured lower-level decision making. We adopt an inverse optimization approach to inform the structure of the lower-level problem from expert demonstrations, ensuring that the objective of the lower-level policy remains aligned with the overall long-term task goal. To validate the approach, our framework is evaluated on distinct decision making tasks: network-based resource allocation and continuous collision avoidance. Empirical results demonstrate that our method consistently outperforms strong baselines based on end-to-end RL, learning-augmented optimal control, and existing hierarchical RL approaches in both efficiency and decision quality.
Social Aspects · Robustness
Ensuring scalable input-to-state stability (sISS) is critical for the safety and reliability of large-scale interconnected systems, especially in the presence of communication delays. While learning-based controllers can achieve strong empirical performance, their black-box nature makes it difficult to provide formal and scalable stability guarantees. To address this gap, we propose a framework to synthesize and verify neural vector Lyapunov-Razumikhin certificates for discrete-time delayed interconnected systems. Our contributions are three-fold. First, we establish a sufficient condition for discrete-time sISS via vector Lyapunov-Razumikhin functions, which enables certification for large-scale delayed interconnected systems. Second, we develop a scalable synthesis and verification framework that learns the neural certificates and verifies the certificates on reachability-constrained delay domains with scalability analysis. Third, we validate our approach on mixed-autonomy platoons, drone formations, and microgrids against multiple baselines, showing improved verification efficiency with competitive control performance.
Applications · Computer Vision
Multimodal sentiment analysis aims to infer human emotions by integrating signals from diverse modalities. However, missing modalities are common in real-world applications due to sensor failure, data corruption, or privacy concerns. Existing approaches typically follow two main paradigms: recovery-based and non-recovery-based methods. This dichotomy results in two critical limitations: I) computational inefficiency and semantic inconsistency (recovery-based methods rely on heavy generators that incur prohibitive inference latency and risk semantic drift due to lack of class-level priors); II) lack of instance specificity (non-recovery-based methods rely on static global mappings that fail to capture sample-specific affective cues). To address these gaps, we propose Adaptive Prototype Imputation (API). To mitigate I), we introduce *Semantic-anchored Class-Temporal Prototype Estimation (SCOPE)* to construct non-trainable prototypes as stable semantic anchors, ensuring semantic reliability. To resolve II), we design *Directional Instance-Adaptive Affine Modulation (DIAM)* to dynamically modulate these anchors via direction-specific affine transformations, capturing instance-unique affective characteristics without generative overhead. Experimental results on CMU-MOSI and CMU-MOSEI demonstrate that API outperforms state-of-the-art baselines, establishing a robust and lightweight prototype-centric paradigm for multimodal sentiment analysis.
Applications · Health / Medicine
Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or masked reconstruction. They often do not adequately capitalize on a key characteristic of physiological features: anatomical structures maintain consistent spatial relationships across individuals (instances), such as the thalamus being medial to the basal ganglia, regardless of variations in brain size, shape, or pathology. We propose leveraging this cross-instance topological consistency as a supervisory signal. The challenge arises from the inherent variability in medical imaging, which can differ significantly across instances and modalities. To tackle this, we focus on two alignment regimes. (i) Intra-instance: with pixel-level correspondences available, a cross-modal triplet objective explicitly preserves local neighborhood topology. (ii) Inter-instance: without such supervision, we derive pseudo-correspondences to control partial neighborhood alignment and prevent topology collapse across modalities. We validate our approach across 7 downstream multi-modal tasks, achieving average improvements of 1.1\% and 5.94\% in segmentation and classification tasks, respectively, and demonstrating significantly better robustness when modalities are missing at test time.
Deep Learning · Large Language Models
Large-scale dedicated application of LLMs in diverse scenarios increasingly demands specialized model inference behavior under strict constraints of accuracy, latency, and memory. However, the heterogeneous and long-tailed nature of real-world specialized scenarios makes it difficult to obtain training data and optimize models. We study a practical inference-time specialization setting: given an LLM base, we compile a reusable, budget-bounded pathway/subnetwork within a specific scenario. Our approach is motivated by an empirical coupling phenomenon: input scenario sets aligned with similar representation subspaces (e.g., domain) in embedding space tend to activate a consistent and sparse set of internal reasoning pathways in model parameter space. To build the bridge between them, we propose probe-based SubspacePath Pruner with two core components: (1) Domain-Basis Synthesis (DBS) constructs a quasi-orthogonal basis of domain axes in embedding space, serving as a stable coordinate system. (2) Probe-based Scenario Pruning (PSP) uses efficient layer-wise linear probes to estimate axis alignment and compute budgeted head-wise pathways for a specific scenario. Experiments on LLaMA-2-13B show 29.3 average Recall on cross-domain tests (vs. 24.7 dense) and 21.6 on cross-dataset tests (vs. 25.5 dense) with 1.27x speedup at ~30% pruning ratio.
General Machine Learning · Clustering
Anchor-based multi-view clustering has garnered wide attention for its ability to reduce the computational complexity of large-scale spectral clustering.However, existing methods mostly adopt a unidirectional optimization paradigm confined to sample-anchor bipartite graphs, treating the construction of the consensus graph and discrete clustering assignments as separate sub-problems to be solved independently. This weakens the information exchange between continuous representation and discrete structure, confining the optimization process to iterative updates within local modules.To address these limitations, we propose a Discretely-Refined Multi-view Clustering(DRMC) via Aligned Anchor Learning. Unlike approaches that directly perform fusion in the anchor space, our method starts from the anchor graph, elevates sample-anchor associations to sample-level similarity graph representations, and thereby enhances both within-cluster similarity and between-cluster separation. Furthermore, we design a discrete feedback module that jointly conducts spectral embedding learning and discrete label assignment by orthogonally aligning the continuous embedding matrix with the discrete indicator matrix. The resulting discrete partition is then fed back into the consensus graph construction, continuously refining the graph structure. Experiments on multiple benchmark datasets demonstrate that the proposed method exhibits significant advantages over existing state-of-the-art approaches.
Deep Learning · Foundation Models
AI developers face a dual-use dilemma. The same capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolved by access control, granting different users access to different AI capabilities. A gold standard for access control would be to serve models with different capabilities to different users. However, training and deploying multiple models is prohibitively expensive. We address this challenge by developing gradient-routed mixture-of-experts (GR-MoE), a pretraining method that selectively updates experts to induce specialization. Ablating an expert at inference time removes its capability, approximating a model trained on filtered data. We evaluate GR-MoE on synthetic stories and realistic dual-use data spanning biology, cybersecurity, nuclear physics, and code. On realistic data, GR-MoE preserves performance on retained capabilities while achieving 30% compute efficiency on forget capabilities. GR-MoE limits recovery more effectively than post-hoc unlearning and preserves capabilities better than LoRA. GR-MoE's advantages improve when scaled from 48M to 2B parameters, approaching multiple data filtered models in a single training run.