32 accepted papers
Large language models (LLMs) have made significant progress in natural language understanding and generation, driven by scalable pretraining and advanced finetuning. However, enhancing reasoning abilities in LLMs, particularly via reinforcement learning from human feedback (RLHF), remains challengin…
The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environments. To facilitate this transition we introduce GEM (General Experience Maker), an open-source environment simulator d…
Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely on a mono-contextual paradigm that accumulates all information in a single, expanding context window, leading to context…
High-quality long-context data is essential for training large language models (LLMs) capable of processing extensive documents, yet existing synthesis approaches using relevance-based aggregation face challenges of computational efficiency. We present LiteLong, a resource-efficient method for synth
We study online change point detection for multivariate inhomogeneous Poisson point process time series. This setting arises commonly in applications such as earthquake seismology, climate monitoring, and epidemic surveillance, yet remains underexplored in the machine learning and statistics literat…
Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like Group Relative Policy Optimization (GRPO). Moreover, existing R
Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet existing approaches exhibit severe accuracy degradation at high sparsity. We show that this failure stems from representational instability: *activation…
Federated Learning (FL) enables decentralized clients to collaboratively train a global model without sharing raw data. However, most existing FL frameworks assume that clients train on static local datasets collected in advance or that the data follows a fixed underlying distribution, which limits …
Large reasoning models (LRMs) achieve strong performance by explicitly generating chain-of-thought (CoT) reasoning, but this reasoning process can be manipulated by adversarial prompts. Inference-time CoT interventions offer a simple and lightweight approach to improving safety, yet existing methods…
Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft–verify mechanism, negating acceleration be…
Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and corresponding ground-truth answers to provide accurate rewards, which requires significant human effort and hinders the sca…
Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based methods typically treat all preference pairs equally, overlooking substantial variations in data quality and learni…
Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents autonomously learn to leverage external tools like code execu…
Length generalization—the ability to solve problems longer than those seen during training—remains a critical challenge for large language models (LLMs). Previous work modifies positional encodings (PEs) and data formats to improve length generalization on specific symbolic tasks such as addition an…
This paper tackles the challenge of anomaly image synthesis and segmentation to generate various anomaly images and their segmentation labels to mitigate the issue of data scarcity. Existing approaches employ the precise mask to guide the generation, relying on additional mask generators, leading to
The Entrance Dependent Vehicle Routing Problem (EDVRP) is a variant of the Vehicle Routing Problem (VRP) where the scale of cities influences routing outcomes, necessitating consideration of their entrances. This paper addresses EDVRP in agriculture, focusing on multi-parameter vehicle planning for
Task-aware navigation continues to be a challenging area of research, especially in scenarios involving open vocabulary. Previous studies primarily focus on finding suitable locations for task completion, often overlooking the importance of the robot’s pose. However, the robot’s orientation is cruci
The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well-studied, Bit-Flip Attacks (BFAs)—which exploit hardware vulnerabilities to corrupt model paramete…
Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-semantic correlations from seen classes. However, most current generative approaches heavily rely on having a sufficient…
Achieving human-like dexterous manipulation remains a crucial area of research in robotics. Current research focuses on improving the success rate of pick-and-place tasks. Compared with pick-and-place, throwing-catching behavior has the potential to increase the speed of transporting objects to thei…
Most previous research on moral frames has focused on social media short texts, little work has explored moral sentiment within news articles. In news articles, authors often express their opinions or political stance through moral judgment towards events, specifically whether the event is right or…
Federated learning has been identified as an efficient decentralized training paradigm for scaling the machine learning model training on a large number of devices while guaranteeing the data privacy of the trainers. FedAvg has become a foundational parameter update strategy for federated learning,…
Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt “post processes” paradigms to improve the performance of LLMs on…
Generating 3D graphs of symmetry-group equivariance is of intriguing potential in broad applications from machine vision to molecular discovery. Emerging approaches adopt diffusion generative models (DGMs) with proper re-engineering to capture 3D graph distributions. In this paper, we raise an ortho…
Knowledge graph embedding (KGE) is an important task and it can benefit lots of downstream applications. General KGE can increase the embedding dimension to improve model performance. High-dimensional KGE will significantly increase the number of model parameters and training time. Therefore, knowle…
In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criteria only guarantee the infinite-time convergence of the system's state to an equilibrium point, which leads to sub-optima…
This paper addresses the problem of localizing and inferring multiple change points, in non-parametric multivariate time series settings. Specifically, we consider a multivariate time series with potentially short-range dependence, whose underlying distributions have Hölder smooth densities and can…
Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency constraints during the training, thus resulting in inefficie…
General domain Named Entity Recognition (NER) datasets like CoNLL-2003 mostly annotate coarse-grained location entities such as a country or a city. But many applications require identifying fine-grained locations from texts and mapping them precisely to geographic sites, e.g., a crossroad, an apart…
Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding constraints. In this paper, for the first time we introduce t…
Previous approaches on 3D shape segmentation mostly rely on heuristic processing and hand-tuned geometric descriptors. In this paper, we propose a novel 3D shape representation learning approach, Directionally Convolutional Network (DCN), to solve the shape segmentation problem. DCN extends convolut…
State-of-the-art i-vector based speaker verification relies on variants of Probabilistic Linear Discriminant Analysis (PLDA) for discriminant analysis. We are mainly motivated by the recent work of the joint Bayesian (JB) method, which is originally proposed for discriminant analysis in face verific…