4 citations · 11 across the 22 of their papers we have counts for
24 papers
Learning from Interaction Experience via Localized Context Distillation
Zhezheng Hao, Yongkang Yang, Xilin Xia +9
Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offers a promising path: privile…
CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection
Qihua Pan, Zhenheng Tang, Peijie Dong +4
Evaluating Large Language Models (LLMs) incurs prohibitive computational overhead during continuous development processes. While coreset selection accelerates evaluation, existing…
Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance
Chao Peng, Zhiheng Lyu, Peijie Dong +2
Long-horizon benchmarks often show that agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. Mo…
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Tencent WorkBuddy Bench Team, Siqi Cai, Shaopeng Chen +35
We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model lea…
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning
Kai Liu, Peijie Dong, Xinchen Xie +5
The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with cont…
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
Xiang Liu, Shimiao Yuan, Zhenheng Tang +5
LLM inference is still evaluated mainly as a model or software problem: accuracy, latency, throughput, and hardware utilization. This is incomplete. At deployment scale, the releva…
VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
Xiaoyan Su, Peijie Dong, Zhenheng Tang +8
Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks essential for profess…
Dissecting Outlier Dynamics in LLM NVFP4 Pretraining
Peijie Dong, Ruibo Fan, Yuechen Tao +11
Training large language models using 4-bit arithmetic enhances throughput and memory efficiency. Yet, the limited dynamic range of FP4 increases sensitivity to outliers. While NVFP…
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
Peijie Dong, Zhenheng Tang, Xiang Liu +3
Post-training compression reduces the computational and memory costs of large language models (LLMs), enabling resource-efficient deployment. However, existing compression benchmar…
The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?
Zhenheng Tang, Xiang Liu, Qian Wang +4
Motivated by reducing the computational and storage costs of LLMs, model compression and KV cache compression have attracted much attention from researchers. However, current metho…
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research
Xiang Liu, Penglei Sun, Shuyan Chen +7
The rapid advancement of perovskite solar cells (PSCs) has led to an exponential growth in research publications, creating an urgent need for efficient knowledge management and rea…
Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing
Kunfeng Lai, Zhenheng Tang, Xinglin Pan +7
Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation…
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
Xiang Liu, Zhenheng Tang, Hong Chen +6
While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the deg…
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Xiang Liu, Zhenheng Tang, Peijie Dong +5
Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Althoug…
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
Zhenheng Tang, Yonggang Zhang, Peijie Dong +4
One-shot Federated Learning (OFL) significantly reduces communication costs in FL by aggregating trained models only once. However, the performance of advanced OFL methods is far b…
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Qi Li, Xiang Liu, Zhenheng Tang +4
Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization,…
LongGenBench: Long-context Generation Benchmark
Xiang Liu, Peijie Dong, Xuming Hu +1
Current long-context benchmarks primarily focus on retrieval-based tests, requiring Large Language Models (LLMs) to locate specific information within extensive input contexts, suc…
LPZero: Language Model Zero-cost Proxy Search from Zero
Peijie Dong, Lujun Li, Xiang Liu +4
In spite of the outstanding performance, Neural Architecture Search (NAS) is criticized for massive computation. Recently, Zero-shot NAS has emerged as a promising approach by expl…
STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
Peijie Dong, Lujun Li, Yuedong Zhong +8
In this paper, we present the first structural binarization method for LLM compression to less than 1-bit precision. Although LLMs have achieved remarkable performance, their memor…
Multi-Task Domain Adaptation for Language Grounding with 3D Objects
Penglei Sun, Yaoxian Song, Xinglin Pan +6
The existing works on object-level language grounding with 3D objects mostly focus on improving performance by utilizing the off-the-shelf pre-trained models to capture features, s…
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models
Peijie Dong, Lujun Li, Zhenheng Tang +4
Despite the remarkable capabilities, Large Language Models (LLMs) face deployment challenges due to their extensive size. Pruning methods drop a subset of weights to accelerate, bu…
VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting
Yujin Tang, Peijie Dong, Zhenheng Tang +2
Combining CNNs or ViTs, with RNNs for spatiotemporal forecasting, has yielded unparalleled results in predicting temporal and spatial dynamics. However, modeling extensive global i…
ParZC: Parametric Zero-Cost Proxies for Efficient NAS
Peijie Dong, Lujun Li, Xinglin Pan +4
Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the efficacy of zero-cost proxies in various NAS benchmarks. Several studies propose the automated desig…
Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models
Longteng Zhang, Xiang Liu, Zeyu Li +8
Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating L…