Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the sequence length increases, which has become a bottleneck for the application of LLMs on long sequences. Existing KV cache compression methods include eviction, merging, or quantization of the KV cache to reduce its size. However, compression results in irreversible information forgetting, potentially affecting the accuracy of subsequent decoding. In this paper, we propose SpeCache, which takes full advantage of the large and easily expandable CPU memory to offload the complete KV cache, and dynamically fetches KV pairs back in each decoding step based on their importance measured by low-bit KV cache copy in VRAM. To avoid inference latency caused by CPU-GPU communication, SpeCache speculatively predicts the KV pairs that the next token might attend to, allowing us to prefetch them before the next decoding step which enables parallelization of prefetching and computation. Experiments on LongBench and Needle-in-a-Haystack benchmarks verify that SpeCache effectively reduces VRAM usage while avoiding information forgetting for long sequences without re-training, even with a 10x high KV cache compression ratio.

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the experts need to be loaded into VRAM. Their large parameter size still limits deployment, and offloading, which load experts into VRAM only when needed, significantly increase inference latency. To address this, we propose Mixture of Lookup Experts (MoLE), a new MoE architecture that is efficient in both communication and VRAM usage. In MoLE, the experts are Feed-Forward Networks (FFNs) during training, taking the output of the embedding layer as input. Before inference, these experts can be re-parameterized as lookup tables (LUTs) that retrieves expert outputs based on input ids, and offloaded to storage devices. Therefore, we do not need to perform expert computations during inference. Instead, we directly retrieve the expert's computation results based on input ids and load them into VRAM, and thus the resulting communication overhead is negligible. Experiments show that, with the same FLOPs and VRAM usage, MoLE achieves inference speeds comparable to dense models and significantly faster than MoE with experts offloading, while maintaining performance on par with MoE.

The applications of large language models (LLMs) in various biological domains have been explored recently, but their reasoning ability in complex biological systems, such as pathways, remains underexplored, which is crucial for predicting biological phenomena, formulating hypotheses, and designing experiments. This work explores the potential of LLMs in pathway reasoning. We introduce BioMaze, a dataset with 5.1K complex pathway problems derived from real research, covering various biological contexts including natural dynamic changes, disturbances, additional intervention conditions, and multi-scale research targets. Our evaluation of methods such as CoT and graph-augmented reasoning, shows that LLMs struggle with pathway reasoning, especially in perturbed systems. To address this, we propose PathSeeker, an LLM agent that enhances reasoning through interactive subgraph-based navigation, enabling a more effective approach to handling the complexities of biological systems in a scientifically aligned manner. The dataset and code are available at https://github.com/zhao-ht/BioMaze.

Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then transferring the models to downstream VL tasks via end-to-end parameter-efficient fine-tuning (PEFT). However, this paradigm still exhibits inefficiency since it significantly increases the input length of the language models. In this paper, in contrast to integrating visual prompts into inputs, we regard visual prompts as additional knowledge that facilitates language models in addressing tasks associated with visual information. Motivated by the finding that Feed-Forward Network (FFN) of language models acts as "key-value memory", we introduce a novel approach termed memory-space visual prompting (MemVP), wherein visual prompts are concatenated with the weights of FFN for visual knowledge injection. Experimental results across various VL tasks and language models reveal that MemVP significantly reduces the training time and inference latency of the finetuned VL models and surpasses the performance of previous PEFT methods. Code: https://github.com/JieShibo/MemVP

Large Language Model (LLM) Agents have recently garnered increasing interest yet they are limited in their ability to learn from trial and error, a key element of intelligent behavior. In this work, we argue that the capacity to learn new actions from experience is fundamental to the advancement of learning in LLM agents. While humans naturally expand their action spaces and develop skills through experiential learning, LLM agents typically operate within fixed action spaces, limiting their potential for growth. To address these challenges, our study explores open-action learning for language agents. We introduce a framework LearnAct with an iterative learning strategy to create and improve actions in the form of Python functions. In each iteration, LLM revises and updates the currently available actions based on the errors identified in unsuccessful training tasks, thereby enhancing action effectiveness. Our experimental evaluations across Robotic Planning and Alfworld environments reveal that after learning on a few training task instances, our approach to open-action learning markedly improves agent performance for the type of task (by 32 percent in AlfWorld compared to ReAct+Reflexion, for instance) highlighting the importance of experiential action learning in the development of more intelligent LLM agents.

Molecule property prediction has gained significant attention in recent years. The main bottleneck is the label insufficiency caused by expensive lab experiments. In order to alleviate this issue and to better leverage textual knowledge for tasks, this study investigates the feasibility of employing natural language instructions to accomplish molecule-related tasks in a zero-shot setting. We discover that existing molecule-text models perform poorly in this setting due to inadequate treatment of instructions and limited capacity for graphs. To overcome these issues, we propose GIMLET, which unifies language models for both graph and text data. By adopting generalized position embedding, our model is extended to encode both graph structures and instruction text without additional graph encoding modules. GIMLET also decouples encoding of the graph from tasks instructions in the attention mechanism, enhancing the generalization of graph features across novel tasks. We construct a dataset consisting of more than two thousand molecule tasks with corresponding instructions derived from task descriptions. We pretrain GIMLET on the molecule tasks along with instructions, enabling the model to transfer effectively to a broad range of tasks. Experimental results demonstrate that GIMLET significantly outperforms molecule-text baselines in instruction-based zero-shot learning, even achieving closed results to supervised GNN models on tasks such as toxcast and muv.

Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our research indicates that token-level alignment is also crucial in multilingual scenarios, which has not been fully explored previously. Based on our findings, we propose a dual-alignment pre-training (DAP) framework for cross-lingual sentence embedding that incorporates both sentence-level and token-level alignment. To achieve this, we introduce a novel representation translation learning (RTL) task, where the model learns to use one-side contextualized token representation to reconstruct its translation counterpart. This reconstruction objective encourages the model to embed translation information into the token representation. Compared to other token-level alignment methods such as translation language modeling, RTL is more suitable for dual encoder architectures and is computationally efficient. Extensive experiments on three sentence-level cross-lingual benchmarks demonstrate that our approach can significantly improve sentence embedding. Our code is available at https://github.com/ChillingDream/DAP.

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current graph transformers suffer from the bottleneck of improving performance by increasing depth. Our further analysis reveals the reason is that deep graph transformers are limited by the vanishing capacity of global attention, restricting the graph transformer from focusing on the critical substructure and obtaining expressive features. To this end, we propose a novel graph transformer model named DeepGraph that explicitly employs substructure tokens in the encoded representation, and applies local attention on related nodes to obtain substructure based attention encoding. Our model enhances the ability of the global attention to focus on substructures and promotes the expressiveness of the representations, addressing the limitation of self-attention as the graph transformer deepens. Experiments show that our method unblocks the depth limitation of graph transformers and results in stateof-the-art performance across various graph benchmarks with deeper models. Transformers have recently gained rapid attention in modeling graph-structured data (Zhang et al., 2020; Dwivedi & Bresson, 2020; Maziarka et al., 2020; Ying et al., 2021; Chen et al., 2022). Compared to graph neural networks, graph transformer implies global attention mechanism to enable information passing between all nodes, which is advantageous to learn long-range dependency of the graph stuctures (Alon & Yahav, 2020). In transformer, the graph structure information can be encoded into node feature (Kreuzer et al., 2021) or attentions (Ying et al., 2021) by a variant of methods flexibly with strong expressiveness, avoiding the inherent limitations of encoding paradigms that pass the information along graph edges. Global attention (Bahdanau et al., 2015) also enables explicit focus on essential parts among the nodes to model crucial substructures in the graph.

In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks. This paper focuses on how to learn a classifier based on a pretrained feature extractor under continual learning setting. We present an probabilistic analysis that the failure of vanilla experience replay (ER) comes from unnecessary re-learning of previous tasks and incompetence to distinguish current task from the previous ones, which is the cause of knowledge degradation and prediction bias. To overcome these weaknesses, we propose a novel replay strategy task-aware experience replay. It rebalances the replay loss and detaches classifier weight for the old tasks from the update process, by which the previous knowledge is kept intact and the overfitting on episodic memory is alleviated. Experimental results show our method outperforms current state-of-the-art methods.

Collaborative Filtering (CF) based recommendation methods have been widely studied, which can be generally categorized into two types, i.e., representation learning-based CF methods and matching function learning-based CF methods. Representation learning tries to learn a common low dimensional space for the representations of users and items. In this case, a user and item match better if they have higher similarity in that common space. Matching function learning tries to directly learn the complex matching function that maps user-item pairs to matching scores. Although both methods are well developed, they suffer from two fundamental flaws, i.e., the representation learning resorts to applying a dot product which has limited expressiveness on the latent features of users and items, while the matching function learning has weakness in capturing low-rank relations. To overcome such flaws, we propose a novel recommendation model named Balanced Collaborative Filtering Network (BCFNet), which has the strengths of the two types of methods. In addition, an attention mechanism is designed to better capture the hidden information within implicit feedback and strengthen the learning ability of the neural network. Furthermore, a balance module is designed to alleviate the over-fitting issue in DNNs. Extensive experiments on eight real-world datasets demonstrate the effectiveness of the proposed model.