Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport

Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in settings such as personalization, where each author requires separate weight access, optimization, storage, and retraining, its costs become prohibitive. We propose Weightless Fine-Tuning (WFT), a training-free decoding-time method that approximates the distributional effect of SFT without weight updates. WFT computes supervised residuals on an author's training sequence and transports them to the current prompt through a cross-prefix transport operator estimated from dropout-induced cross-covariance. The operator captures how a perturbation at one context propagates to predictions at another, replacing gradient-based parameter updates with logit-space corrections. On three LaMP personalization benchmarks, WFT achieves the best average performance across datasets, matches or exceeds SFT on individual tasks, and outperforms other lightweight baselines on average. In a budget-controlled comparison, WFT approaches SFT performance using less than 7% of the effective computation. Logit-level analysis shows a cosine similarity of 0.875 between the logit shifts induced by WFT and SFT over 95% of the next-token probability mass, suggesting that WFT captures the distributional effect of supervised adaptation without modifying model weights.

A Wearable Stiffness-Rendering Haptic Device with a Honeycomb Jamming Mechanism for Bilateral Teleoperation

This paper addresses the challenge of providing kinesthetic feedback in bilateral teleoperation by designing a wearable, lightweight (20 g), and compact haptic device, the HJ-Haptic, utilizing a honeycomb jamming mechanism for object stiffness rendering. The HJ-Haptic device can vary its stiffness, from 1.15 N/mm to 2.64 N/mm, using a 30 kPa vacuum pressure. We demonstrate its implementation in a teleoperation framework, enabling operators to adjust grip force based on a reliable haptic feedback on object stiffness. A three-point flexural test on the honeycomb jamming mechanism and teleoperated object-grasping tasks were conducted to evaluate the device's functionality. Our experiments demonstrated a small RMSE and strong correlations in teleoperated motion, stiffness rendering, and interaction force feedback. The HJ-Haptic effectively adjusts its stiffness in response to real-time gripper feedback, mimicking the sensation of direct object grasping with hands. The device's use of vacuum pressure ensures operator safety by preventing dangerous outcomes in case of gas leakage or material failure. Incorporating the HJ-Haptic into the teleoperation framework provided the reliable perception of object stiffness and stable teleoperation. This study highlights the potential of the honeycomb jamming mechanism for enhancing haptic feedback in various applications, including teleoperation scenarios, as well as interactions with extended-reality environments.

Consistent Feature Transport for Image Relighting

Image relighting modifies illumination while preserving non-lighting content such as identity and geometry. Existing diffusion-based methods often suffer from unstable illumination changes or inconsistent content preservation under complex lighting, as they lack an explicit mechanism to learn feature transformations between images. We reformulate relighting as an illumination feature transport problem and introduce Consistent Feature Transport (CFT), a training principle that explicitly enforces illumination-consistent transport between source and target image distributions. Built upon rectified flow, CFT jointly models noise-to-image generation and illumination-consistent source-to-target transport through trajectory-level supervision. This dual-transport formulation encourages isolation of illumination-specific variations while preserving content-aligned features. To support complex lighting scenarios, we construct a large-scale portrait relighting dataset with diverse relighting effects. Experiments show consistent improvements over existing state-of-the-art relighting approaches and demonstrate that CFT can generalize to other editing tasks, including style transfer. Code is available at https://github.com/Dixin-Lab/CFT.

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate isolated operations such as single-formula generation or local cell edits, and therefore fail to capture end-to-end workflows in realistic business settings. We introduce \textsc{SpreadsheetBench 2}, a workflow-level benchmark for spreadsheet agents that covers three task categories: generation, debugging, and visualization. The benchmark is constructed from authentic business data, including financial reports and corporate filings, and is annotated and validated by domain experts. The benchmark contains 321 tasks; each instance averages 11.8 worksheets and requires 593.5 cell modifications, reflecting large multi-sheet workbooks with cross-sheet dependencies. We evaluate eight frontier large language models under a unified multi-turn agent scaffold, and additionally include several LLM-based spreadsheet products as complementary baselines. Results show that current systems remain far from reliable on real-world workflows: the best model achieves 34.89\% overall task accuracy, and debugging accuracy is as low as 12.00\%. Trajectory analysis and a failure taxonomy further indicate that insufficient spreadsheet inspection and incorrect target-cell selection are the dominant bottlenecks. Together, these findings position \textsc{SpreadsheetBench 2} as a challenging testbed for advancing reliable spreadsheet automation. Project page: https://spreadsheetbench.github.io/

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-designs the efficient teacher-forcing layout with SP execution by pairing clean-history and noisy-target temporal chunks on each rank, enabling a natural teacher-forcing mask with SP-aware chunked VAE encoding. Combined with NVFP4 precision, it reduces GPU memory cost and accelerates GEMM computation during training, the proportion of which increases as video length grows. Moreover, we show that a high-quality infrastructure and dataset enable a remarkably clean training pipeline. Unlike existing Self-Forcing series methods that rely on ODE initialization and subsequent distribution matching distillation (DMD), LongLive-2.0 directly tunes a diffusion model into a long, multi-shot, interactive auto-regressive (AR) diffusion model. It can be further converted to real-time generation (4 to 2 denoising steps) with standalone LoRA weights. For inference on Blackwell GPUs, we enable W4A4 NVFP4 inference, quantize KV cache into NVFP4 for memory savings, and boost end-to-end throughput with asynchronous streaming VAE decoding. On non-Blackwell GPU architectures, we deploy SP inference to match the speed on Blackwell GPUs, while the quantized KV cache can lower inter-GPU communication of SP. Experiments show up to 2.15x speedup in training, and 1.84x in inference. LongLive-2.0-5B achieves 45.7 FPS inference while attaining strong performance on benchmarks. To our knowledge, LongLive-2.0 is the first NVFP4 training and inference system for long video generation.

PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery

On-the-Fly Category Discovery (OCD) requires a model, trained on an offline support set, to recognize known classes while discovering new ones from an online streaming sequence. Existing methods focus heavily on offline training. They aim to learn discriminative representations on the support set so that novel classes can be separated at test time. However, their discovery mechanism at inference is typically reduced to a single threshold. We argue that this paradigm is fundamentally flawed as OCD is not a static classification problem, but a dynamic process. The model must continuously decide 1) whether a sample belongs to a known class, 2) matches an existing novel category, or 3) should initiate a new one. Moreover, prior methods treat the support set as fixed knowledge. They do not update their decision boundaries as new evidence arrives during inference. This leads to unstable and inconsistent category formation. Our experiments confirm these issues. With properly calibrated and adaptive thresholds, substantial improvements can be achieved, even without changing the representation. Motivated by this, we propose PACO, a support-set-calibrated, tree-structured online decision framework. The framework models inference as a sequence of hierarchical decisions, including known-class routing, birth-aware novel assignment, and attach-versus-create operations over a dynamic prototype memory. Furthermore, we simulate the proxy discovery process to initialize the thresholds during offline training to align with inference. Thresholds are continuously updated during inference using mature novel prototypes. Importantly, PACO requires no heavy training and no dataset-specific tuning. It can be directly integrated into existing OCD pipelines as an inference-time module. Extensive experiments show significant improvements over SOTA baselines across seven benchmarks.

Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery

On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during inference, using supervision only from known classes during offline training. Existing approaches rely either on fixed label supervision or on diffusion-based augmentations to enhance the backbone, yet none of them explicitly train the model to perform the discovery task required at test time. It is fundamentally unreasonable to expect a model optimized on limited labeled data to carry out a qualitatively different discovery objective during inference. This mismatch creates a clear optimization misalignment between the offline learning stage and the online discovery stage. In addition, prior methods often depend on hash-based encodings or severe feature compression, which further limits representational capacity. To address these issues, we propose Learning through Creation (LTC), a fully feature-based and hash-free framework that injects novel-category awareness directly into offline learning. At its core is a lightweight, online pseudo-unknown generator driven by kernel-energy minimization and entropy maximization (MKEE). Unlike previous methods that generate synthetic samples once before training, our generator evolves jointly with the model dynamics and synthesizes pseudo-novel instances on the fly at negligible cost. These samples are incorporated through a dual max-margin objective with adaptive thresholding, strengthening the model's ability to delineate and detect unknown regions through explicit creation. Extensive experiments across seven benchmarks show that LTC consistently outperforms prior work, achieving improvements ranging from 1.5 percent to 13.1 percent in all-class accuracy. The code is available at https://github.com/brandinzhang/LTC

From Folding Mechanics to Robotic Function: A Unified Modeling Framework for Compliant Origami

Origami inspired architectures offer a powerful route toward lightweight, reconfigurable, and programmable robotic systems. Yet, a unified mechanics framework capable of seamlessly bridging rigid folding, elastic deformation, and stability driven transitions in compliant origami remains lacking. Here, we introduce a geometry consistent modeling framework based on discrete differential geometry (DDG) that unifies panel elasticity and crease rotation within a single variational formulation. By embedding crease panel coupling directly into a mid edge geometric discretization, the framework naturally captures rigid folding limits, distributed bending, multistability, and nonlinear dynamic snap through within one mechanically consistent structure. This unified description enables programmable control of stability and deformation across rigid and compliant regimes, allowing origami structures to transition from static folding mechanisms to active robotic modules. An implicit dynamic formulation incorporating gravity, contact, friction, and magnetic actuation further supports strongly coupled multiphysics simulations. Through representative examples spanning single fold bifurcation, deployable Miura membranes, bistable Waterbomb modules, and Kresling based crawling robots, we demonstrate how geometry driven mechanics directly informs robotic functionality. This work establishes discrete differential geometry as a foundational design language for intelligent origami robotics, enabling predictive modeling, stability programming, and mechanics guided robotic actuation within a unified computational platform.

CoSA: Compressed Sensing-Based Adaptation of Large Language Models

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a practical paradigm for adapting large language models (LLMs) without updating all parameters. Most existing approaches, such as LoRA and PiSSA, rely on low-rank decompositions of weight updates. However, the low-rank assumption may restrict expressivity, particularly in task-specific adaptation scenarios where singular values are distributed relatively uniformly. To address this limitation, we propose CoSA (Compressed Sensing-Based Adaptation), a new PEFT method extended from compressed sensing theory. Instead of constraining weight updates to a low-rank subspace, CoSA expresses them through fixed random projection matrices and a compact learnable core. We provide a formal theoretical analysis of CoSA as a synthesis process, proving that weight updates can be compactly encoded into a low-dimensional space and mapped back through random projections. Extensive experimental results show that CoSA provides a principled perspective for efficient and expressive multi-scale model adaptation. Specifically, we evaluate CoSA on 10 diverse tasks, including natural language understanding and generation, employing 5 models of different scales from RoBERTa, Llama, and Qwen families. Across these settings, CoSA consistently matches or outperforms state-of-the-art PEFT methods.

ContextBench: A Benchmark for Context Retrieval in Coding Agents

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks. Data and code are available at: https://cioutn.github.io/context-bench/.