Large language models (LLMs) have achieved remarkable breakthroughs across various applications. However, their architectures remain inefficient in pretraining due to two main limitations: (i) self-attention lacks an explicit inductive bias for locality, leading to redundant modeling of sequence-internal local information; (ii) mixture-of-experts (MoE) implicitly couples knowledge storage with computational pathways, hindering flexible access to sequence-external global knowledge. To overcome these limitations, we propose LoKiFormer, a novel LLM architecture that augments the standard decoder with two dedicated modules: 1) Local Fusion Attention (LFA), which incorporates a convolutional fusion to attention, explicitly capturing local patterns and allowing the attention to operate on more informative representations; 2) Knowledge Memory Module (KMM), which introduces a parametric key–value memory that explicitly stores global knowledge in addressable slots, decoupling storage from computation and enabling direct knowledge retrieval. Together, these modules enable LoKiFormer to achieve more efficient and effective integration of information at both levels. Experimental results show that LoKiFormer converges 1.33x faster in pre-training than baseline models, underscoring its superiority over existing LLM architectures.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address this challenge. DockSmith treats environment construction not merely as a preprocessing step, but as a core agentic capability that exercises long-horizon tool use, dependency reasoning, and failure recovery, yielding supervision that transfers beyond Docker building itself. DockSmith is trained on large-scale, execution-grounded Docker-building trajectories produced by a SWE-Factory--style pipeline augmented with a loop-detection controller and a cross-task success memory. Training a 30B-A3B model on these trajectories achieves open-source state-of-the-art performance on Multi-Docker-Eval, with 39.72\% Fail-to-Pass and 58.28\% Commit Rate. Moreover, DockSmith improves out-of-distribution performance on SWE-bench Verified, SWE-bench Multilingual, and Terminal-Bench 2.0, demonstrating the broader agentic benefits of environment construction. Our model and Docker-building trajectories are publicly available at https://huggingface.co/collections/8sj7df9k8m5x8/docksmith.
Self-evolving memory systems are rapidly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve on the fly within environment interactions. However, this paradigm is fundamentally constrained by the \textit{staticity} of the memory system itself: while memory facilitates agent-level evolving, the underlying memory architecture cannot be meta-adapted to diverse task contexts. To address this gap, we propose MemEvolve, a meta-evolutionary framework that jointly evolves agents’ experiential knowledge and their memory architecture, allowing agent systems not only to accumulate experience but also to progressively refine how they learn from it. To ground MemEvolve in prior work and promote openness in future self-evolving systems, we introduce EvolveLab, a unified memory codebase that distills twelve representative memory systems into a modular design space (\textit{encode}, \textit{store}, \textit{retrieve}, \textit{manage}), providing a standardized implementation substrate and a fair experimental arena. Extensive evaluations on four challenging agentic benchmarks show that MemEvolve delivers (i) substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to $17.06\%$, and (ii) strong cross-task and cross-LLM generalization, yielding memory architectures that transfer effectively across diverse benchmarks and backbones.
Applications · Chemistry, Physics, and Earth Sciences
Symbolic regression (SR) aims to discover interpretable mathematical expressions from observed data. While recent generative approaches have shown promise in treating SR as machine translation or multimodal learning tasks using NN methods, they suffer from a fundamental limitation: training-evaluation misalignment. The training objectives (average cross-entropy loss on a token level across the distribution of historical data) differ from the evaluation metric (fitting error for every test data / complexity), necessitating extensive heuristic post-processing and constant optimization. On the other hand, direct optimization methods suffer from curse of dimensionality, non-differentiability and local optima traps. We propose MOD-SR, unifying multimodal distribution learning during training with direct optimization at inference time. This is achieved by modeling the task as $p(x_0 \mid \mathcal{D}, y^*)$ and employing gradient-guided diffusion in embedding space, enhanced by contrastive learning and representation alignment. Furthermore, we introduce DFEX, a fixed-depth tree relaxation method that ensures differentiability for effective gradient guidance during inference. Experiments demonstrate significant improvements over existing methods, achieving superior performance on diverse benchmarks through a unified framework integrating distribution learning and optimization.
Recent years have witnessed significant progress in developing effective diffusion models. Parallel sampling is a promising recent approach that reformulates the sequential denoising process as solving a system of nonlinear equations, and it can be combined with other acceleration techniques. However, current progress is limited by the trade-off between high fidelity and computational efficiency. This paper addresses the challenge of scaling to high-dimensional, multi-modal generation. Specifically, we present ROPA (Robust Parallel Diffusion Sampling), which takes into account the properties of the denoising process and solves the linear system using adaptive local sparsity to achieve stable parallel sampling. Extensive experiments demonstrate ROPA’s effectiveness: it significantly accelerates sampling across diverse image and video diffusion models, achieving up to $2.9\times$ speedup with eight core, an improvement of 52\% over baselines without sacrificing sample quality. ROPA enables parallel sampling methods to provide a solid foundation for real-time, high-fidelity diffusion generation.
Applications · Chemistry, Physics, and Earth Sciences
Efficient sampling of molecular systems at thermodynamic equilibrium is a hallmark challenge in statistical physics. This challenge has driven the development of Boltzmann Generators (BGs), which allow rapid generation of uncorrelated equilibrium samples by combining a generative model with exact likelihoods and an importance sampling correction. However, modern BGs predominantly rely on Normalizing Flows (NFs), which either suffer from limited expressivity due to strict invertibility constraints (discrete time) or computationally expensive likelihoods (continuous time). In this paper, we propose Autoregressive Boltzmann Generators (ArBG), a novel autoregressive modelling framework that overcomes these limitations by departing from the flow-based BG paradigm. ArBG circumvents the topological constraints of flows and enables sequential inference-time interventions, while offering enhanced scalability by leveraging architectures effective in Large Language Models. We empirically demonstrate that ArBG leads to significant improvements over flow-based models across all benchmarks, but particularly in larger peptide systems such as the 10-residue Chignolin. Furthermore, we introduce Robin, a 132M parameter transferable model trained with the ArBG framework which improves over the previous state-of-the-art, reducing the zero-shot energy error, $\mathcal{E}$-$\mathcal{W}_2$, on 8-residue systems by $\sim 60$\%.
General Machine Learning · Everything Else
In personalized federated learning (PFL), collaboration graphs specify model aggregation among clients. However, without constraints on the collaboration geometry, training can drift into two degenerate regimes: global consensus or spontaneous clustering. This paper provides a unified dynamical analysis: under the same budget of representative models, collaborative PFL is more expressive and achieves higher-order approximation accuracy than clustered PFL. An upper bound on disagreement further reveals two degeneration mechanisms—overly strong collaboration drives consensus (reducing to standard federated learning), while similarity-driven weight updates make the graph nearly reducible and induce self-clustering (collapsing to clustered PFL). Motivated by these findings, we propose pFedCCG. pFedCCG preserves the expressivity advantage via controlled collaboration geometry (CCG): it builds a static similarity-based collaboration template decoupled from training, optimizes a Markovian collaboration matrix with a prescribed stationary distribution via reversible parameterization and Euclidean projection, and schedules collaboration strength to avoid self-clustering. Experiments across diverse heterogeneity settings show consistent personalization gains and markedly reduced collapse and self-clustering. Code will be available at https://anonymous.4open.science/r/pFedCCG-CB88.
Deep Learning · Large Language Models
Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. The hidden risk is that incidental prompt cues can steer \emph{which} algorithm is selected, even when all outputs pass the same tests. Prompt sensitivity is well studied as a tool to improve output quality, but we instead examine output policy: algorithm choice under fixed correctness. We define algorithm steering and run 55{,}545 controlled experiments across 11 tasks, 19 cue types (18 channels plus a memoization ablation), and 15 models. We find large, interpretable shifts in algorithm-family distributions (up to 100 percentage points, pp), including on applied tasks such as rate limiting, yielding an ``invisible lottery'' in which accidental context alters performance, security, and maintainability.
Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for few-step samplers. We introduce a temporal difference (TD) objective that penalizes inconsistency of the model’s \emph{multi-step} progress along the denoising path. By reformulating the diffusion process as a Markov reward process and casting denoising as a policy evaluation problem in reinforcement learning, we derive a unified TD approach that applies to both discrete- and continuous-time diffusion formulations. We further propose a principled sample-based reweighting method that stabilizes training. Empirically, we show that using our TD training can significantly improve sample quality measured by FID, with stronger advantages when the number of sampling steps is small, highlighting its practical utility under low-computation-budget scenarios. We provide ablation studies to justify our design choices, including pairwise loss reweighting, regularization weight, and one-step stride. Overall, our TD approach can be a general drop-in that enforces cross-time consistency and improves generation quality across different diffusion generative models.
Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we find that in large language model training, DST suffers from optimization instability, manifested as loss spikes following topology updates. In this work, we show that the naive use of standard Adam-based optimizers leads to a cold-start issue for newly regrown parameters, resulting in excessively large updates and disrupted training dynamics. We propose Sparse Memory-Efficient Training (SMET), which stabilizes DST by combining optimizer warm-up for regrown parameters with density-aware learning-rate scaling. SMET further reduces memory consumption by storing gradients and optimizer states only for active parameters. We provide a theoretical analysis of the update behaviors under SMET, showing improved optimization stability. Extensive experiments demonstrate that SMET enables stable, scalable, and memory-efficient sparse pre-training of LLMs, paving the way for sparse training as a practical alternative to dense training.
Deep Learning · Everything Else
Estimating the generalization gap and developing optimization methods that improve generalization are crucial for deep learning models, for both theoretical understanding and practical applications. Leveraging unlabeled data for these purposes offers significant advantages in real-world scenarios. This paper introduces a novel generalization measure, $\textit{local inconsistency}$, derived from an information-geometric perspective on the parameter space of neural networks. A key feature of local inconsistency is that it can be computed without explicit labels. We establish theoretical underpinnings by connecting local inconsistency to the Fisher information matrix and the loss Hessian. Empirically, we demonstrate that local inconsistency correlates with the generalization gap. Based on these findings, we propose Inconsistency-Aware Minimization (IAM), which incorporates local inconsistency into the training objective. We demonstrate that in standard supervised learning settings, IAM enhances generalization, achieving performance comparable to that of existing methods such as Sharpness-Aware Minimization. Furthermore, IAM exhibits efficacy in semi- and self-supervised learning scenarios, where the local inconsistency is computed from unlabeled data.
Applications · Computer Vision
In open-world settings, thermal infrared (TIR) image degradations continuously emerge and evolve, while most existing all-in-one restoration methods are built on a closed-set assumption and struggle to continually adapt to novel degradations. To address this, we propose ECMRNet, an Expandable, Compressible, and Mineable Restoration Network for open-world TIR restoration from the perspective of continual degradation learning. Conceptually, ECMRNet unifies continual degradation learning as an ``expand–compress–mine'' closed-loop process, enabling sustained adaptation to new degradations with controllable evolution. Structurally, ECMRNet decomposes intermediate representations into group-isolated subspaces, and achieves strict parameter isolation and fast adaptation to new degradations by freezing historical groups and isomorphically expanding new ones. To curb model growth as tasks accumulate, we present Structural Entropy Pruning, which identifies and removes redundant channel groups via two-dimensional structural entropy minimization, achieving information contribution–driven adaptive compression. Moreover, we design a Sub-degradation Knowledge Mining module that dynamically retrieves and recombines transferable components from historical representations to improve restoration under compound degradations. Experimental results demonstrate that ECMRNet achieves superior overall performance across diverse single and compound degradations while using fewer parameters and lower computational cost, highlighting its scalability and efficiency in open-world TIR restoration.
Large Language Models (LLMs) obey consistent scaling laws---empirical power-law fits that predict how loss decreases with compute, data, and parameters. While predictive, these laws are descriptive rather than prescriptive: they characterize typical training, not optimal training. Surprisingly few works have successfully challenged the data-efficiency bounds implied by these laws---which is our primary focus. To that end, we introduce the Geodesic Hypothesis, positing that token sequences trace geodesics on a smooth semantic manifold and are therefore locally linear. Building on this principle, we propose a novel Semantic Tube Prediction (STP) task, a JEPA-style regularizer that confines hidden-state trajectories to a tubular neighborhood of the geodesic. STP generalizes JEPA to language without requiring explicit multi-view augmentations. We show this constraint improves signal-to-noise ratio, and consequently preserves diversity by preventing trajectory collisions during inference. Empirically, STP allows LLMs to match baseline accuracy with 16$\times$ less training data, directly violating the data term of Chinchilla-style scaling laws and demonstrating that principled geometric priors can surpass brute-force scaling.
Reinforcement Learning · Deep RL
Ensuring safe behavior in reinforcement learning (RL) is challenging when safety constraints are implicit and cannot be densely measured. In many settings, supervision is limited to coarse approvals or rejections of whole trajectories (e.g., whether a rollout remained within an unknown safety threshold). We propose **TraCeS** (Trajectory-based Constraint Estimation for Safety), a method for learning **per-timestep violation credit** from such sparse trajectory-level labels. **TraCeS** trains a sequential violation estimator whose per-step credits factorize the predicted probability that a trajectory has **not yet violated** the constraint, and integrates this learned signal into constrained policy optimization. The method requires neither a known cost function nor a known threshold, and remains compatible with standard continuous-control algorithms. We provide a theoretical analysis of the approximation gap introduced by the learning objective, and demonstrate empirically that **TraCeS** improves constraint satisfaction and feedback efficiency over baselines across multiple continuous-control benchmarks, including long-horizon tasks and settings with noisy or inconsistent labels.
Probabilistic Methods · Monte Carlo and Sampling Methods
Slice sampling is a standard Monte Carlo technique for Dirichlet process (DP)--based models, widely used in posterior simulation. However, formal assessments of the scalability of posterior slice samplers have remained largely unexplored, primarily because the computational cost of a slice-sampling iteration is random and potentially unbounded. In this work, we obtain high-probability bounds on the computational complexity of DP slice samplers. Our main results show that, uniformly across posterior cluster-growth regimes, the overhead induced by slice variables, relatively to the number of clusters supported by the posterior, is $O_{\mathbb P}(\log n)$. As a consequence, even in worst-case configurations, superlinear blow-ups in per-iteration computational cost occur with vanishing probability. Our analysis applies broadly to DP--based models without any likelihood-specific assumptions, still providing complexity guarantees for posterior sampling on arbitrary datasets. These results establish a theoretical foundation for assessing the practical scalability of slice sampling in DP-based models.
Reinforcement Learning · Everything Else
Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL) alignment stage. The main reason is that RL alignment typically requires either expensive human preference annotation or heavy reliance on high-quality reward models with large-scale API usage and ongoing engineering maintenance, both of which are ill-suited to on-premise settings. To bridge this gap, in this paper, we propose a positive-unlabeled (PU) RL distillation method for on-premise small-model deployment. Without human-labeled preferences or a reward model, our method distills the teacher’s preference-optimization capability from black box generations into a locally trainable student. For each prompt, we query the teacher once to obtain an anchor response, locally sample multiple student candidates, and perform anchor-conditioned self-ranking to induce pairwise or listwise preferences, enabling a fully local training loop via direct preference optimization or group relative policy optimization. Theoretical analysis justifies that the induced preference signal by our method is order-consistent and concentrates on near-optimal candidates, supporting its stability for preference optimization. Experiments demonstrate that our method achieves consistently strong performance under a low-cost setting.
Deep Learning · Large Language Models
Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and substantial computational overhead. We propose Video-OPD, an efficient post-training framework for TVG inspired by recent advances in on-policy distillation. Video-OPD optimizes trajectories sampled directly from the current policy, thereby preserving alignment between training and inference distributions, while a frontier teacher supplies dense, token-level supervision via a reverse KL divergence objective. This formulation preserves the on-policy property critical for mitigating distributional shift, while converting sparse, episode-level feedback into fine-grained, step-wise learning signals. Building on Video-OPD, we introduce Teacher-Validated Disagreement Focusing (TVDF), a lightweight training curriculum that iteratively prioritizes trajectories that are both teacher-reliable and maximally informative for the student, thereby improving training efficiency. Empirical results demonstrate that Video-OPD consistently outperforms GRPO while achieving substantially faster convergence and lower computational cost, establishing on-policy distillation as an effective alternative to conventional reinforcement learning for TVG.
Applications · Language, Speech and Dialog
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this challenge, we propose a goal-oriented clarification framework that aligns clarification behavior with ambiguity resolution. Central to our approach is the Information Gain Reward, a metric that quantifies the utility of clarification questions by measuring the Bayesian belief update towards the ground-truth goal induced by the clarification exchange. We train the clarifier (LLM) using this reward to optimize for high information gain, ensuring that clarifications effectively reduce uncertainty and improve task completion within the agent-tool-user environment. We validate our framework within a clarification-enhanced $\tau$-Bench environment, conducting cross-agent evaluations across five heterogeneous backbones. Empirical results demonstrate that our method consistently improves the success rate by 3.7\% over the no-clarification baseline, incurring small overhead via surgical interventions (averaging only 0.3 additional steps). Our code and data are available at the anonymous repository: \url{https://anonymous.4open.science/r/Information-Gain-Clarifier-AD68/}.
Deep Learning · Large Language Models
Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of existing KD methods and present a unified view that establishes connections between them, reformulating KD as a reweighted log-likelihood objective at the token level. We further propose Hybrid Policy Distillation (HPD), which integrates the complementary advantages of forward and reverse KL to balance mode coverage and mode-seeking behaviors, and combines off-policy data with lightweight approximate on-policy sampling. We validate HPD on long-generation math reasoning as well as short-generation dialogue and code tasks, demonstrating improved optimization stability, computational efficiency, and final performance across diverse model families and scales.
Given that simulation can never exhaustively enumerate reality, generalization is the determining factor for whether Vision-Language-Action (VLA) models can translate benchmark success into real-world functionality. However, current evaluation protocols often incentivize mechanical memorization rather than robust policy learning, leading to a paradoxical duality of failure: high-scoring models exhibit *spurious invariance* to semantic changes while simultaneously displaying *extreme brittleness* to trivial environmental perturbations. To address this, we introduce **LIBERO-Gen**, a diagnostic benchmark systematically designed to shift evaluation from intuition-driven heuristics to explicit distributional assumptions. Through a hierarchical protocol spanning **In-distribution**, **Compositional**, and **Domain Generalization**, LIBERO-Gen reveals performance stratifications previously masked by standard metrics. Our analysis identifies Pi0.5 as the top performer (64.0% in Spatial-CG; 21.2% in Task-CG). By identifying perceptual instability and action binding collapse as primary failure modes while validating the efficacy of structured ``Stair” sampling, LIBERO-Gen establishes a rigorous baseline for deployment reliability.