50 articles mentioning Efficient-DLM-4B
arXiv:2610.27384v1 Announce Type: new Abstract: We analytically study the evolution of the energy function of Dense Associative Memories (DenseAMs) as they train on randomly sampled codewords of random expander low-density parity-check codes (a.k.a. solutions of random XORSAT problems). We identify
arXiv:2610.28200v1 Announce Type: cross Abstract: Accurate electrical load forecasting supports power-system operation across countries, regions, cities, and buildings, but repeated development of target-specific models is costly. Time series foundation models (TSFMs) provide reusable pretrained bac
arXiv:2610.26995v1 Announce Type: new Abstract: LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading incurs high token and runtime overhead. In contrast, flat semantic retrieval treats skills as i
arXiv:2610.27367v1 Announce Type: new Abstract: Reflective prompt optimization improves instructions using task feedback, but coupling candidate generation with full-validation-based selection can make search costly and sequential. We propose a two-stage framework that decouples reflective candidate
arXiv:2610.28584v1 Announce Type: new Abstract: Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) offer parallelism but lack semantic coherence. To addresses both limitations, we propose Collaborative Reasoning Asymmetric Learning (Co
arXiv:2610.04693v3 Announce Type: replace Abstract: Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature and carries real penalties. Whether an omission is material, or a disclosure sufficient, depends on what the response left out. Probing such an o
arXiv:2602.08062v2 Announce Type: replace Abstract: Large Language Models have demonstrated remarkable capabilities in natural language understanding. However, they remain susceptible to malicious prompts that induce unsafe or policy-violating behavior. Existing defenses in black-box moderation APIs
arXiv:2610.27078v1 Announce Type: new Abstract: We introduce Lookup-table (LUT)-aware Efficient Attention on FPGAs (LEAF). LEAF is the first nanosecond-scale LUT-aware transformer for FPGAs. Deploying transformers that are large enough to perform well, small enough to fit on an FPGA, and fast enough
arXiv:2610.27670v1 Announce Type: new Abstract: This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound design significantly influences gameplay and accessibility; however, objective evaluation methods, defi
arXiv:2603.03595v2 Announce Type: replace Abstract: Coordinating multiple autonomous agents to explore and serve spatially heterogeneous demand requires jointly learning unknown spatial patterns and planning trajectories that maximize task performance. Pure model-based approaches provide structured
arXiv:2610.21436v2 Announce Type: replace Abstract: Device-cloud speculative decoding reduces server computation, but growing a deep draft tree with a small language model (SLM) requires repeated passes on a mobile neural processing unit (NPU). We present HyCo, which runs the server model's native m
arXiv:2610.27699v1 Announce Type: new Abstract: Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar quantization encodes weights independently, while explicit-codebook vector quantization introduces c
arXiv:2610.28618v1 Announce Type: new Abstract: Graph generative models commonly use graph-specific Transformer architectures to jointly update node and edge features. However, these architectures do not directly benefit from recent hardware-aware attention implementations, limiting their scalabilit
arXiv:2602.10971v3 Announce Type: replace Abstract: We consider heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions and propose \texttt{HCW-GLB-OMD}, a simple algorithm that combines an online mirror descent (OMD)-based estimator with Hessian-based confidence weights. Alth
arXiv:2609.37976v2 Announce Type: replace-cross Abstract: LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capacity lies in the Thinking model's weight component within the null space of a projection define
arXiv:2408.01503v3 Announce Type: replace Abstract: Combinatorial optimization problems near algorithmic phase transitions represent a fundamental challenge for both classical algorithms and machine learning approaches. Among them, graph coloring is a prototypical constraint satisfaction problem cha
arXiv:2610.27813v1 Announce Type: new Abstract: Multi-agent systems rely on communication to complete tasks, and latent communication passes continuous representations to reduce text generation and re-encoding. However, multi-agent systems must reconfigure agent models, whereas existing latent-commu
arXiv:2610.28555v1 Announce Type: cross Abstract: Statistical learning in high dimensions suffers from the curse of dimensionality. Fortunately, many functions of practical interest are compositionally sparse, meaning they admit a composition of local functions, each depending on only a few variable
arXiv:2604.19444v2 Announce Type: replace Abstract: Reasoning language models often lack the calibrated confidence needed for reliable deployment, particularly when correctness labels are unavailable and sampling budgets are limited. We introduce Binary Agreement for Self-consistency Calibration (BA
arXiv:2610.27598v1 Announce Type: new Abstract: As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hierarchical architectures, where experts in different layers, although topological
arXiv:2510.13003v2 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates interfere with the dominant singular directions that encode essential pre-trained knowledge. We propose Or
arXiv:2610.27106v1 Announce Type: cross Abstract: We present the Sparse Particle-interaction Transformer Architecture (SParTA), a modular, scalable, and efficient transformer for jet tagging at high-energy colliders. Exploiting the steeply falling transverse-momentum ($p_T$) spectrum of jet constitu
arXiv:2610.22858v1 Announce Type: cross Abstract: Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal utility of expansion. We first show, across existing search algorithms, that continu
arXiv:2610.23145v1 Announce Type: cross Abstract: Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to store all network activations until the loss gradient has been propagated back th
arXiv:2602.04926v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has become a standard approach for knowledge-intensive LLM tasks. Complex reasoning remains challenging because queries often require composing dispersed evidence through multiple dependent reasoning steps
arXiv:2610.22597v1 Announce Type: new Abstract: Personally Identifiable Information (PII) detection models must efficiently find identifiers across diverse contexts while maintaining a low false-positive rate (FPR) on high-volume traffic. Recent detectors increasingly rely on complex architectures t
arXiv:2610.22883v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as a prevalent strategy for adapting large pre-trained models. Among PEFT techniques, reparameterization-based methods, particularly those that employ low-rank or sparsity structures, have attracted si
arXiv:2507.20130v2 Announce Type: replace Abstract: Recent breakthroughs in generative models have shown great promise for drug discovery, yet Structure-Based Drug Design (SBDD) faces two critical challenges: the scarcity of high-quality protein-ligand complex data and the practical synthesizability
arXiv:2610.23006v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making expert offloading necessary for memory-constrained inference. However, existing sy
arXiv:2610.21329v1 Announce Type: new Abstract: Attribute-value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging strategies for extracting the attribute names and their corresponding values. Tagging models directl
arXiv:2610.08258v2 Announce Type: replace Abstract: Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We pres
arXiv:2604.22560v2 Announce Type: replace-cross Abstract: Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We present
arXiv:2610.17831v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are appealing for code generation because they can update many tokens in parallel, yet many are optimized for sequence synthesis rather than edit prediction. This setting is poorly matched to modern AI-assisted
arXiv:2606.17029v2 Announce Type: replace Abstract: Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria that translate report quality
arXiv:2610.18007v1 Announce Type: cross Abstract: LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf of a user. Existing checker-repair defenses can reduce inappropriate disclosure, but they rely on re
arXiv:2610.05998v2 Announce Type: replace Abstract: Molecular dynamics simulations proceed by integrating the Langevin equations over many small femtosecond timesteps. This poses a challenge for estimating ensemble properties and transition dynamics that occur on much longer timescales. We introduce
arXiv:2610.18862v1 Announce Type: cross Abstract: Reasoning models achieve strong performance through long chains of thought (CoT), but often spend more tokens than needed to solve a problem. Existing ways to shorten the CoT require additional training for each model, add a fixed steering vector to
arXiv:2610.16857v1 Announce Type: cross Abstract: Research on video classification models has witnessed significant growth recently, accompanied by a significant increase in the demand for datasets to train such models. Existing video dataset curation approaches share a common bottleneck: candidate
arXiv:2610.17552v1 Announce Type: cross Abstract: Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled models are difficult to align with human preferences. These challenges c
arXiv:2610.16415v1 Announce Type: new Abstract: Industrial recommendation rankers keep scaling in width and depth to billions of parameters, but this increasingly incurs costs in parameter growth, distributed communication overhead, and training inefficiency. We introduce \underline{C}hain \underlin
arXiv:2606.13898v3 Announce Type: replace-cross Abstract: Creative image editing tools, such as Adobe Photoshop's Remove and Generative Fill buttons, are central to everyday customer use and account for a major share of traffic. However, current generative AI models face significant latency challeng
arXiv:2610.18014v1 Announce Type: cross Abstract: Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks. However, when agents have conflicting tasks, directly reusing non-prefix KV caches across agents can
arXiv:2602.11965v2 Announce Type: replace Abstract: Temporal domain generalization (TDG) learns from a sequence of observed domains to predict models for unseen future domains. Existing parameter-dynamics methods become prohibitively expensive at modern backbone scales because their temporal encoder
arXiv:2610.19026v1 Announce Type: new Abstract: Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely operate at coarse granularity. Token-level selection offers finer control, yet presents two challenges: low-dimensional scoring may lo
arXiv:2601.12243v3 Announce Type: replace-cross Abstract: Video summarization transforms long videos into concise representations that are easier to document and analyze, especially in high-stakes domains such as surgical training. However, long-form videos often require dense frame processing or su
arXiv:2610.17625v1 Announce Type: cross Abstract: For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated generation at different times and viewpoints. We introduce 4LC, a 4D latent cache with composite visua
arXiv:2610.19408v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open challenge. Any-order generation can suffer from entropy degradation, which narrows the reasoning paths
arXiv:2610.16212v1 Announce Type: cross Abstract: Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late training checkpoints, obscuring differences in convergence efficiency. We introduce
arXiv:2601.12355v3 Announce Type: replace Abstract: To lower the expertise barrier in machine learning, the AutoML community has focused on the CASH problem, which jointly automates algorithm selection and hyperparameter tuning. While traditional methods like Bayesian Optimization (BO) struggle with
arXiv:2610.19738v1 Announce Type: new Abstract: Large protein language models provide a powerful framework for learning sequence-function relationships and guiding experimental design. However, architectural improvements are underexplored, especially in low-compute regimes of relevance for resource-