Haoran Jin

Yiyou Sun, Xinyang Han, Weichen Zhang et al.

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

Ruijie Gao, Haoran Jin, Jirong Yang et al.

Numerous tensor accelerator designs have been proposed, yet most lack well-documented ISAs and compiler backends, limiting evaluation to a handful of operators. Recent work has shown that given a tensor-level ISA specification, complete software stacks including compiler backends can be automatically generated--but writing such specifications remains a manual, expert-driven process. We present ATLAAS, the first end-to-end MLIR-based pipeline that lifts RTL-extracted accelerator semantics to tensor ISA specifications. Starting from bit-level LLVM IR produced by prior architecture-level model extraction, ATLAAS applies an 8-pass semantic lifting pipeline that progressively recovers high-level tensor structure--MAC idioms, saturation semantics, multi-dimensional buffer organizations, and data layout transformations--emitting specifications that immediately enable automatic software stack generation through the ACT ecosystem. We evaluate ATLAAS on the Gemmini systolic-array accelerator, where the pipeline collapses bit-level MLIR by up to 92.9% on processing elements and 24-34% on controller modules. ATLAAS discovers hardware features omitted from the hand-written reference, with correctness validated via Z3 SMT equivalence proofs. Generality is confirmed on TVM's VTA processor, where the same pipeline lifts all four datapath modules without accelerator-specific changes, enabling an automated path from RTL to a performance-competitive compiler backend.

Qi Liu, Xuyang Hou, Haoran Jin et al.

Extracting users' interests from their lifelong behavior sequence is crucial for predicting Click-Through Rate (CTR). Most current methods employ a two-stage process for efficiency: they first select historical behaviors related to the candidate item and then deduce the user's interest from this narrowed-down behavior sub-sequence. This two-stage paradigm, though effective, leads to information loss. Solely using users' lifelong click behaviors doesn't provide a complete picture of their interests, leading to suboptimal performance. In our research, we introduce the Deep Group Interest Network (DGIN), an end-to-end method to model the user's entire behavior history. This includes all post-registration actions, such as clicks, cart additions, purchases, and more, providing a nuanced user understanding. We start by grouping the full range of behaviors using a relevant key (like item_id) to enhance efficiency. This process reduces the behavior length significantly, from O(10^4) to O(10^2). To mitigate the potential loss of information due to grouping, we incorporate two categories of group attributes. Within each group, we calculate statistical information on various heterogeneous behaviors (like behavior counts) and employ self-attention mechanisms to highlight unique behavior characteristics (like behavior type). Based on this reorganized behavior data, the user's interests are derived using the Transformer technique. Additionally, we identify a subset of behaviors that share the same item_id with the candidate item from the lifelong behavior sequence. The insights from this subset reveal the user's decision-making process related to the candidate item, improving prediction accuracy. Our comprehensive evaluation, both on industrial and public datasets, validates DGIN's efficacy and efficiency.

Haoran Jin, Meng Li, Xiting Wang et al.

Aligning Large Language Models (LLMs) with human values has attracted increasing attention since it provides clarity, transparency, and the ability to adapt to evolving scenarios. In this paper, we introduce a Controlled Value Vector Activation (ConVA) method that directly aligns the internal values of LLMs by interpreting how a value is encoded in their latent representations and modifies relevant activations to ensure consistent values in LLMs. To ensure an accurate and unbiased interpretation, we propose a context-controlled value vector identification method. To consistently control values without sacrificing model performance, we introduce a gated value vector activation method for effective and minimum degree of value control. Experiments show that our method achieves the highest control success rate across 10 basic values without hurting LLM performance and fluency, and ensures target values even with opposite and potentially malicious input prompts. Source code and data are available at~ https://github.com/hr-jin/ConVA.

Meng Li, Haoran Jin, Ruixuan Huang et al.

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by LLMs. Yet their evaluation poses unique challenges, especially due to their non-local nature and high dimensional representation in a model's hidden space. Current methods approach concepts from different perspectives, lacking a unified formalization. This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging. To bridge the gap, we introduce a formal definition of concepts generalizing to diverse concept-based explanations' settings. Based on this, we quantify the faithfulness of a concept explanation via perturbation. We ensure adequate perturbation in the high-dimensional space for different concepts via an optimization problem. Readability is approximated via an automatic and deterministic measure, quantifying the coherence of patterns that maximally activate a concept while aligning with human understanding. Finally, based on measurement theory, we apply a meta-evaluation method for evaluating these measures, generalizable to other types of explanations or tasks as well. Extensive experimental analysis has been conducted to inform the selection of explanation evaluation measures.

Qiuyu Chen, Xin Jin, Yue Song et al.

This paper reviews the 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real), held in conjunction with ICCV 2025. The workshop aimed to bridge the gap between the theoretical promise of Disentangled Representation Learning (DRL) and its application in realistic scenarios, moving beyond synthetic benchmarks. DRL4Real focused on evaluating DRL methods in practical applications such as controllable generation, exploring advancements in model robustness, interpretability, and generalization. The workshop accepted 9 papers covering a broad range of topics, including the integration of novel inductive biases (e.g., language), the application of diffusion models to DRL, 3D-aware disentanglement, and the expansion of DRL into specialized domains like autonomous driving and EEG analysis. This summary details the workshop's objectives, the themes of the accepted papers, and provides an overview of the methodologies proposed by the authors.