arXiv subjects

Yanzhi Wang

Publications and source records attributed to Yanzhi Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels

Edge LLM deployment is shaped by more than model size and precision: inference backend, hardware platform, memory traffic, and power management all affect latency and efficiency. We present Hydra, a common-schema, phase-aware workload characterization framework for LLM inference on edge SoCs. Hydra instruments HuggingFace Transformers and llama.cpp with a shared per-prompt timing schema and fuses those records with hardware telemetry, enabling a multi-dimensional characterization of performance, system-resource utilization, and efficiency across prefill and decode phases. Using Hydra, we evaluate three consecutive edge System-on-Chip (SoC) generations (AGX Xavier, AGX Orin, and AGX Thor), 13 instruction-tuned LLMs from seven families, five execution formats, and consider input/output-length sensitivity. The resulting artifact contains roughly 107K per-prompt records and is publicly released with Hydra. Our analysis shows that aggregate latency alone hides key deployment effects: backend structure changes where latency is introduced, quantization reduces memory traffic and energy but does not predict power monotonically, and SoC generation changes how utilization and efficiency should be interpreted. By connecting phase-level timing with system-resource utilization and efficiency metrics, Hydra enables reproducible, phase-aware characterization of edge LLM inference. Hydra's source code and the collected per-prompt trace corpus are available open-source at: https://github.com/amirtaherin/hydra

cs.AR↗

arXiv2026

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoning introduces substantial computational latency and resource overhead, which can interrupt action execution and reduce system reliability. Excessive reasoning may delay actions, while insufficient reasoning often leads to incorrect decisions and task failures. This raises a fundamental question for embodied agents: when should the agent reason, and when should it act? In this work, we propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents. Rather than learning low-level control policies, RARRL learns a high-level orchestration policy that operates at the agent's decision-making layer. This policy enables the agent to adaptively determine whether to invoke reasoning, which reasoning role to employ, and how much computational budget to allocate based on current observations, execution history, and remaining resources. Extensive experiments, including evaluations with empirical latency profiles derived from the ALFRED benchmark, show that RARRL consistently improves task success rates while reducing execution latency and enhancing robustness compared with fixed or heuristic reasoning strategies. These results demonstrate that adaptive reasoning control is essential for building reliable and efficient embodied robotic agents.

cs.RO↗

arXiv2026

Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation

While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current practice requires training a separate Low-Rank Adaptation (LoRA) module for each effect, incurring substantial data curation and iterative optimization costs that hinder interactive control. We present Prompt2Effect, a weight-driven hypernetwork that amortizes per-effect training by directly synthesizing effect-specific LoRA weights in a single forward pass. Unlike prior hypernetworks that regress adapter weights purely from semantics, Prompt2Effect is explicitly conditioned on the frozen base model weights, grounding prediction in the structural geometry of each layer. Furthermore, instead of predicting raw LoRA matrices, we introduce an SVD-canonicalized parameterization that resolves factorization ambiguity and stabilizes large-scale synthesis. Extensive experiments demonstrate that Prompt2Effect achieves on-par or superior video quality and effect alignment compared to conventional LoRA fine-tuning, while reducing the computational cost from 56 GPU training hours to 3.3 seconds of hypernetwork inference. When used as initialization for subsequent fine-tuning, our predicted weights further improve final performance and accelerate optimization by approximately 10x.

cs.CV↗

arXiv2026

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache footprint, memory traffic, latency, and energy. Context compression offers a natural remedy by pruning retrieved text before generation. However, state-of-the-art context-compression methods are typically used with a fixed compression budget, or with the rate selected offline and then applied at inference time. This static view ignores both workload variation and the live state of the edge device. On an edge SoC, compression is not free: the compressor itself runs on the same SoC and consumes latency and energy that can offset any generation savings. This paper proposes a vision for telemetry-informed adaptive compression in edge RAG, grounded in experimental evidence. We characterize the compression tradeoff on the NVIDIA Jetson AGX Thor using Llama and Qwen generators, Natural Questions and HotpotQA datasets, and LLMLingua-2 compression. Our measurements show that generation dominates the RAG budget for larger models, reaching roughly 90% of per-query latency and 91% of GPU energy for 7B-8B generators. Exploring the impact of the compression rate reveals an adaptive operating region: mild compression can miss energy opportunities, and overly aggressive compression can hurt inference quality. Intermediate compression can reduce GPU energy by up to 53.2%, and SoC energy by up to 48.2%, with negligible quality loss. We argue for runtime policies that dynamically manage compression, guided by workload features and edge telemetry.

cs.AI↗

arXiv2026

Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B

Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series prediction. While LLMs display in-context learning capabilities, the mechanisms with which they accomplish time-series prediction remain unclear. Specifically, whether they truly understand the underlying structure, which at a minimum requires reasoning over first differences in the sequence of numbers. To study this, we investigate Llama 3.1-8B from a mechanistic interpretability point of view. Mechanistic interpretability is an emerging field concerned with the reverse engineering of the algorithms learned by neural networks such as LLMs. To assess Llamas' numerical sequence modeling capabilities and to facilitate our mechanistic interpretability analysis, we create a sequence modeling task that cannot be solved without picking up structural cues. Specifically, we sample n random numbers and repeat them with an offset. We find that Llama displays strong performance on our tasks suggesting that it can pick up on the underlying structure. To understand the mechanisms that allow it to do so, we perform probing experiments and activation patching based counterfactual analysis. Probing reveals that the model computes and stores first differences in its internal representations without explicit supervision, indicating that it tracks structural information about the sequence. Activation patching reveals that Llama retrieves the relevant first-difference with a mechanism similar to an induction circuit and subsequently adds it to the current value. Notably, our work represents one of the first studies to identify this form of concept induction in LLMs.

cs.LG↗

arXiv2026

Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT

Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vulnerabilities while preserving the functional behavior of legacy systems. Large language models (LLMs) have shown promise for this task but typically underperform when applied off-the-shelf, since general-purpose pretraining rarely emphasizes idiomatic Rust generation, cross-language semantic equivalence, or the ability to reason about and repair compiler/runtime feedback. In this report we describe a three-stage fine-tuning curriculum applied to Qwen3-27B that is designed to progressively specialize the model for the C-to-Rust (C2Rust) translation task: (1) continued pretraining on Rust-centric corpora to strengthen the model's prior over idiomatic Rust syntax and standard-library usage; (2) supervised fine-tuning (SFT) on the microsoft/Verus_Training_Data dataset to instill debugging and self-repair behavior over Rust code; and (3) task-specific SFT on paired C/Rust solutions derived from LeetCode problems to teach direct semantic translation. We evaluate the resulting model using the agentic, static-analysis-guided verification framework of SACTOR, which performs structure-aware, two-phase (unidiomatic to idiomatic) translation with foreign-function-interface (FFI)-based end-to-end (E2E) testing. We report success rate, idiomaticity (Clippy lint counts, unsafe-code fraction), and failure-mode analyses, and compare our fine-tuned model against baseline Qwen3-27B and other LLMs evaluated under the same framework.

cs.SE↗

arXiv2026

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: (1) an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; (2) an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce OmniModel.cpp, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through OmniModel.cpp. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on $π_{0.5}$. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB (5.3$\times$). On the physical UR3 arm, $π_{0.5}$ quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5$\times$.

cs.CV↗

arXiv2026

VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading to high inference latency and increased training cost, and (ii) insufficient utilization of generated actions resulting in potential performance loss. To address these issues, we develop a training framework to finetune VLA models for generating significantly fewer action tokens with high parallelism, effectively reducing inference latency and training cost. Furthermore, we introduce an inference optimization technique with a novel voting-based ensemble strategy to combine current and previous action predictions, improving the utilization of generated actions and overall performance. Our results demonstrate that we achieve superior performance compared with state-of-the-art VLA models, achieving significantly higher success rates and 39$\times$ faster inference than OpenVLA with 46 Hz throughput on edge platforms, demonstrating practical deployability. The code is available at https://github.com/LukeLIN-web/VOTE.

cs.CV↗

arXiv2026

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models

Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters. Our preliminary analysis reveals that rescaling activations in selected transformer layers-without modifying pretrained weights-can significantly influence downstream performance. Motivated by this observation, we propose ScAle, an ultra-lightweight adaptation method that learns a small set of scalar coefficients to modulate last-token attention and MLP activations in a fully frozen backbone. We evaluate our method on the synthetic spatial reasoning benchmark SpatialEval and on real-world VQA datasets (COCOQA and VGQA) across multiple model families. Our method, ScAle, achieves up to 134.1% relative accuracy gains using only 1K trainable parameters without requiring millions of trainable parameters as in standard PEFT methods such as LoRA. Despite its extreme compactness, our approach recovers a substantial fraction of standard PEFT performance while preserving strong non-spatial VQA accuracy. These results demonstrate that bounded activation reweighting provides a simple, architecture-agnostic, and highly parameter-efficient alternative for adapting pretrained VLMs.

cs.CV↗

arXiv2026

Human Cognition in Machines: A Unified Perspective of World Models

This report of world models distinguishes prior works by the cognitive functions they innovate. Many works claim an almost human-like cognitive capability in their world models. To evaluate these claims requires a proper grounding in first principles from human and machine cognition theory. In moving towards human-like world models we present a conceptual unified framework for world models that fully incorporates all the cognitive functions (i.e., memory, perception, language, reasoning, imagining, motivation, and metacognition) and identify gaps in existing research as a guide for future states of the art. In particular, we find that motivation (especially intrinsic motivation) and metacognition remain drastically under-researched, and we propose concrete directions to address these gaps informed by active inference and global workspace theory. We also introduce epistemic world models, a new category encompassing agent frameworks for scientific discovery that operate over structured knowledge. Our taxonomy, applied to video, embodied, and epistemic world models, suggests research directions where prior taxonomies have not.

cs.RO↗

arXiv2026

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation

Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. Existing methods reduce this cost by truncating the KV cache or compressing it into implicit memory, but both lose explicit access to query-relevant historical details. We propose OmniMem, an explicit full-range memory retrieval framework that performs sparse KV retrieval over the historical cache. To make this practical for chunk-based AR video generation, OmniMem addresses two issues: (i) local bias in sparse KV selection and (ii) Union Explosion in memory access. Adaptive Window Exclusion removes local-window blocks from the selection candidates when sufficient long-range history is available, preserving the sparse budget for informative long-range retrieval. Query-Shared KV Selection reduces cross-query diversity, while Per-Head Scattered KV Access avoids expanding head-specific selections into a large selected KV buffer. This allows each attention head to retrieve non-contiguous KV blocks according to its own selection pattern. Experiments on long-video generation show that OmniMem improves Dynamic Degree by 52.3% and preserves strong consistency over strong baselines, while maintaining comparable memory usage.

cs.CV↗

arXiv2026

Structured Agent Distillation for Large Language Model

Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks. Yet, their practical deployment is constrained by high inference costs and large model sizes. We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models while preserving both reasoning fidelity and action consistency. Unlike standard token-level distillation, our method segments trajectories into [REASON] and [ACT] spans, applying segment-specific losses to align each component with the teacher's behavior. This structure-aware supervision enables compact agents to better replicate the teacher's decision process. Experiments on ALFWorld, HotPotQA-ReAct, and WebShop show that our approach consistently outperforms token-level and imitation learning baselines, achieving significant compression with minimal performance drop. Scaling and ablation results further highlight the importance of span-level alignment for efficient and deployable agents.

cs.LG↗

arXiv2026

PhyWorld: Physics-Faithful World Model for Video Generation

World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse and realistic visual futures. However, using them as world simulators requires physically faithful video continuations, namely, generated videos that preserve the physical state implied by the conditioning input, and evolve in ways consistent with basic physical principles. We propose PhyWorld, a video generation world model designed to produce temporally coherent and physically faithful scene continuations through two-stage post-training. In the first stage, we improve video-to-video continuation with flow matching fine-tuning, encouraging stable visual attributes and coherent motion dynamics across frames. In the second stage, we align generated dynamics with physical principles using Direct Preference Optimization (DPO) over physics preference pairs, guiding the model toward outputs with higher physical plausibility. To evaluate PhyWorld, we use both standard video-quality benchmarks and a dedicated physical-faithfulness benchmark with per-law scoring. Experiments show that PhyWorld improves video consistency, achieving an average score of 0.769 on VBench compared with 0.756 or below for state-of-the-art baselines. PhyWorld also improves physical plausibility, reaching an average score of 3.09 on our physical-faithfulness benchmark compared with 2.99 for the strongest baseline. These results suggest that post-training large video generation models with continuation and physics-preference signals can make them more effective world simulators for Physical AI.

cs.CV↗

arXiv2026

PanoWorld: Geometry-Consistent Panoramic Video World Modeling

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly constrain the underlying 3D scene state, producing outputs that appear plausible yet exhibit inconsistent depth, broken correspondences, and implausible motion across the spherical surface. We address this gap by framing panoramic video generation as a geometry- and dynamics-consistent latent state modeling problem rather than pure visual synthesis. Building on a pre-trained perspective video world model, we introduce two lightweight regularizers: a depth consistency loss against pseudo ground-truth panoramic depth, and a trajectory consistency loss that supervises the 3D world-frame positions of tracked points across time. We further apply spherical-geometry-aware adaptation to the conditioning and positional encoding. We additionally introduce PanoGeo, a unified geometry-aware panoramic video dataset with consistent depth, trajectory, and prompt annotations across diverse real and synthetic sources, used for both training and stratified evaluation. Experiments show that PanoWorld improves geometric consistency over prior panoramic generation methods while maintaining competitive visual realism, establishing that panoramic video generation must be treated as a geometric modeling problem to support the holistic spatial understanding requirements of embodied AI applications. Code is available at https://github.com/ostadabbas/PanoWorld.

cs.CV↗

arXiv2026

PhyGround: Benchmarking Physical Reasoning in Generative World Models

Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these rules remains challenging. Existing physics-focused video benchmarks have made important progress, but they still face three key challenges, including the coarse evaluation frameworks that hide law-specific failures, response biases and fatigue that undermine the validity of annotation judgments, and automated evaluators that are insufficiently physics-aware or difficult to audit. To address those challenges, we introduce PhyGround, a criteria-grounded benchmark for evaluating physical reasoning in video generation. The benchmark contains 250 curated prompts, each augmented with an expected physical outcome, and a taxonomy of 13 physical laws across solid-body mechanics, fluid dynamics, and optics. Each law is operationalized through observable sub-questions to enable per-law diagnostics. We evaluate eight modern video generation models through a large-scale, quality-controlled human study, grounded on social science lab experiment design. A total of 459 annotators provided 5,796 complete annotations and over 37.4K fine-grained labels; after quality control, the retained annotations exhibited high split-half model-ranking correlations (Spearman's rho > 0.90). To support reproducible automated evaluation, we release PhyJudge-9B, an open physics-specialized VLM judge. PhyJudge-9B achieves substantially lower aggregate relative bias than Gemini-3.1-Pro (3.3% vs. 16.6%). We release prompts, human annotations, model checkpoints, and evaluation code on the project page https://phyground.github.io/.

cs.CV↗

arXiv2026

CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs

Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a benchmark that evaluates generated CUDA against end-to-end human-expert SOTA systems. It spans single kernels, module-level operators, full applications, and unsolved challenge tasks across Ampere, Hopper, and Blackwell GPUs, with end-to-end tasks gated by domain-specific semantic validators. Evaluating models such as Claude-Opus-4.6 and GPT-5.4 shows a large gap between runnable CUDA and expert CUDA engineering: models often compile and pass tests, but rarely recover the optimization strategies needed to match expert performance. Application semantics further reduce success, and iterative or tool-augmented feedback can improve correctness while drifting toward slow fallback implementations. These results show that automated CUDA programming remains far from fully solved and requires stronger hardware reasoning, better tool use, and training objectives that connect code understanding to hardware architecture-grounded intelligence.

cs.LG↗

arXiv2026

Efficient Reasoning with Hidden Thinking

Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities in Multimodal Large Language Models (MLLMs). However, the verbose nature of textual reasoning introduces significant inefficiencies. In this work, we propose Heima (as hidden llama), an effective CoT compression framework that condenses lengthy CoTs into a small set of abstract thinking tokens, preserving essential reasoning while removing redundancy. We then conduct a theoretical analysis from an information-theoretic perspective, quantifying the information gap induced by compression, showing that reasoning capability is preserved when non-trivial mutual information is retained. To further explore and quantify this information gap, we design the adaptive interpreter that maps thinking tokens back to variable-length textual sequences, thereby reconstructing the reasoning process. Experiments across diverse reasoning benchmarks demonstrate that Heima improves reasoning efficiency, while maintaining or even achieving better zero-shot accuracy. Moreover, the interpreter reconstructs coherent reasoning progresses from compressed thinking tokens, revealing that the information gap is minimal and validating the effectiveness of the proposed framework. This work paves the way for scalable latent reasoning models and advances our understanding of efficient reasoning processes in large models. Code: https://github.com/shawnricecake/Heima

cs.CL↗

arXiv2026

From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs

Deploying models, especially large language models (LLMs), is becoming increasingly attractive to a broader user base, including those without specialized expertise. However, due to the resource constraints of certain hardware, maintaining high accuracy with larger model while meeting the hardware requirements remains a significant challenge. Model quantization technique helps mitigate memory and compute bottlenecks, yet the added complexities of tuning and deploying quantized models further exacerbates these challenges, making the process unfriendly to most of the users. We introduce the Hardware-Aware Quantization Agent (HAQA), an automated framework that leverages LLMs to streamline the entire quantization and deployment process by enabling efficient hyperparameter tuning and hardware configuration, thereby simultaneously improving deployment quality and ease of use for a broad range of users. Our results demonstrate up to a 2.3x speedup in inference, along with increased throughput and improved accuracy compared to unoptimized models on Llama. Additionally, HAQA is designed to implement adaptive quantization strategies across diverse hardware platforms, as it automatically finds optimal settings even when they appear counterintuitive, thereby reducing extensive manual effort and demonstrating superior adaptability. Code will be released.

cs.LG↗