This paper proposes a context engineering approach that scales memory with distinct information instead of tokens, using a novelty-gated cache and state-space summary.

The paper introduces HOLA (Hippocampal Linear Attention), a semiparametric test-time memory system that combines a compressive linear-attention state with a bounded exact cache for key-value associati…

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

ElasticMem introduces a novel framework that treats memory as an elastic latent resource, allowing LLM agents to adaptively manage and inject variable-budget memories for improved performance in long-…

The paper introduces Reasoning in Memory (RiM), a latent reasoning method that replaces autoregressive token generation with fixed memory blocks to enable compute-efficient internal working memory for…

Moment-KV introduces a novel momentum-based technique to compress the Key-Value (KV) cache during the decoding phase of LLM generation, significantly improving fidelity in long-generation tasks.

The paper introduces Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that enables abstract intermediate computation to persist across dec…

The paper demonstrates that the location and nature of state encoding in sequence models are not fixed architectural traits but are highly dependent on the specific task, showing that the encoding pro…

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…

The paper proposes adaptive caching for key-value (KV) caching in large language models, improving cache hit rate and reducing time to first token.

The paper quantifies the exact parametric memory capacity of LLMs using LoRA and proposes a new optimization strategy, MemFT, to enhance memory fidelity.

The paper proposes AsymCache, a computation-latency-aware KV cache management system that optimizes LLM inference by aligning cache eviction decisions with GPU attention kernel performance, significan…

The paper reframes context distillation as a latent memory management problem, proposing a modular framework using LoRA adapters and a Self-Gating mechanism for efficient, selective memory retrieval a…

The paper introduces Entity-Collision, a rigorous protocol that separates genuine retrieval lift from simple lexical overlap, demonstrating that embedder performance depends critically on the query ty…

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper demonstrates that positional encodings are not necessary for transformers to achieve universal computation, showing that the inherent mechanism of sliding context windows already provides su…

The paper introduces Curvature-Conditioned Query (CCQ), a novel read-time contraction mechanism that improves linear attention's performance on long-context and retrieval tasks by incorporating the ge…