Spotlight

Papers

Field

Top tools here

Coming with more sources: stars history

All tools

NVIDIA Dynamo+60% downloads · 15.8k/wk+60.0%
BentoML+30% downloads · 41k/wk+29.7%
MLX+26% downloads · 342.6k/wk+25.5%
Open WebUI3 releases this week
mlx-lm+8% downloads · 140.9k/wk+7.5%

Top tools here

Open problems in Inference & serving

Efficient long-horizon context management3 papers raise it · 3 address it
Long-horizon agents need to retain and use relevant information without exceeding finite context windows.
- REMORY: Learning Residual Memory for Context Compactionraises · addresses
- Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agentsraises · addresses
- MemT-1.0: Towards Memory-Native Evolutionraises · addresses
Token-level LLM routing efficiency1 paper raises it · 1 addresses it
Fine-grained token-level routing improves cost-quality trade-offs but strains existing serving systems.
- TokenRouter: Efficient Serving System for Token-Level LLM Routingraises · addresses
Memory-induced sycophancy in agents1 paper raises it · 1 addresses it
Persistent memories can cause agents to over-align with user beliefs, even when they are incorrect or outdated.
- Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancyraises · addresses
Quality gap in parallel token generation2 papers raise it · 2 address it
Diffusion language models generate tokens in parallel but lag behind autoregressive models in quality.
- ALoDLM: Adaptively Looped Diffusion Language Modelsraises · addresses
- Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Modelsraises · addresses
Sparse attention computation overhead1 paper raises it · 1 addresses it
Sparse attention reduces computation but still requires scoring all keys, limiting efficiency gains.
- DoSA: Dots Sparse Attentionraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Market

EMode PhotonixPre-seed · Oct 16$1M
MueonSeries A · Oct 15$65M
TrimagnetixSeed · Oct 15$1M
ModalSeries B+ · Oct 14$750M
Salience LabsSeries B+ · Oct 14$125M

Recently funded

Topics in this field

agent memory · memory construction · term memory248 papers54 this week
gpus · gpu · throughput212 papers32 this week
diffusion language models · language models diffusion · models diffusion language145 papers29 this week
sparse attention · linear attention · attention layers131 papers24 this week
continual learning · catastrophic forgetting · forgetting230 papers22 this week
aware routing · model routing · model llm routing82 papers20 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

★ Spotlight this month

arXiv cs.DCOct 15▲ 2

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Muhammad Ibrahim

Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly back the per-engine cache with a remote tier shared by every engine. We study such a tier in a disaggregated deployment of GLM-5.3, an FP8 mixture-of-experts model with multi-head latent attention (MLA), on 8xB300 nodes running prefill context parallelism (PCP8). Enabling the remote tier (LMCache with a Valkey store) left median time-to-first-token unchanged but raised the 16k-token p99 from 3.96 s to 17.3 s. Replaying a production request stream on an isolated engine, we find that a remote hit took 0.88 s against 0.31 s to recompute the prompt, and that synchronous loading turned a hit-heavy stream into an unstable queue: p99 83.32 s with the GPUs 7% busy. A two-term cost model explains both: a hit pays off only if the tier delivers more than B* = sR (2.53 GB/s for this model and GPU), and a fixed per-hit engine cost (T0 ~ 0.33 s) means that hits on prompts shorter than about 17k tokens cannot beat recompute at any bandwidth. Guided by the model, we (i) shard the MLA KV store across PCP ranks, with a proof that the existing…

PDF arXiv page Details

Spotlight

Recent papers

All in Research →

arXiv cs.CLCodeOct 19▲ 6
Competing Learning in Hybrid Architectures
Xingyu Shen, Yingfa Chen, Ziqing Qiao, Chaojun Xiao, Xu Han +1
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly expressive mixing mechanism while ensuring high throughput by compressing contextual information into a fixed-size state, but underperform softmax attention in contextual information retrieval. In this paper, we reveal a Competing Learning phenomenon where different kinds of mixers compete to learn the same function, and when any layer learns a function, it suppresses the corresponding learning signal for other layers. Layer attribution analysis reveals that under typical data distributions, modern recurrence learns retrieval functions faster than softmax attention, causing attention to fail to learn retrieval in most cases. Stopping weight updates in recurrence in the middle of training helps attention learn retrieval. Based on these results, we propose a staged training procedure for pre-training hybrid architectures on natural language. Empirical results on models up to 1B parameters show that our method results in substantial improvement in language modeling loss, common-sense reasoning, as well as a wide…
PDF arXiv Code
arXiv cs.CLCodeOct 19▲ 106
MemT-1.0: Towards Memory-Native Evolution
Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi +69
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano and MemT-1.0-Flash, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction…
PDF arXiv Code
arXiv cs.AICodeOct 19▲ 7
Remembering Has a Price: Learning Memory Worth under Resource Constraints
Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang, Han-Jia Ye
Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such stringent joint constraints, we find that existing lifelong-memory methods can become ineffective, with several sophisticated approaches offering little advantage over simple retrieval or even no-memory agents. This reveals a more fundamental problem: resource scarcity makes each memory decision more consequential. When only a small amount of past experience can be retained or reused and opportunities for reasoning and recovery are limited, retrieving a relevant but ineffective memory can consume scarce context and hinder downstream execution. The key challenge is therefore not simply to retrieve relevant experience, but to determine which experiences are actually worth retaining and reusing. To address this challenge, we propose TokenWorth, a lightweight online memory framework that learns query-dependent memory worth from sparse execution feedback and applies it consistently to memory retrieval and bounded memory management. Across three LifelongAgentBench environments and both local and…
PDF arXiv Code
arXiv cs.CLCodeOct 17▲ 5
ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction
Yuxuan Zhou, Junyuan Shang, Tianyu Wang, Chunrui Zheng, Zichang Liu +3
Existing Multi-token prediction (MTP) methods are auxiliary by design: the multi-horizon loss mostly trains modules attached to the backbone, and each added horizon costs another module and another pass. We propose Efficient Causal Self-Recursion (ECHO), which removes both costs. The backbone's own final layer predicts every horizon, so the supervision lands on the parameters that generate the next token, and Dynamic Depth Sampling (DDS) keeps deeper horizons affordable by drawing the training depth with probabilities that decay along depth. Future prediction thus becomes part of the autoregressive objective rather than a task attached to it, and the gains follow on both sides of it. In pretraining, added depth converts into downstream accuracy where auxiliary modules saturate, concentrating on reasoning and code at half the MTP training overhead of training every depth. At inference, the pretrained model is its own drafter: it drafts beyond the depth it was trained for, and keeps its draft-target alignment on the open-ended, high-entropy generation where post-hoc drafters lose theirs. The advantage survives a doubled token budget, a repeated pretraining run, and supervised…
PDF arXiv Code
arXiv cs.CLCodeOct 16▲ 21
DLite: History-free Speculative Decoding for Agentic AI
Jiaming Xu, Hanzhen Wang, Tianlang Zhao, Jiewen Xiao, Chengze Yuan +5
Speculative decoding has become a mainstream technique for accelerating large language model (LLM) inference by using a lightweight draft model to generate candidate tokens that are subsequently verified by the target model. However, agentic workloads introduce long and continuously evolving contexts and frequent multi-turn interactions. Under such workloads, we observe that existing draft models suffer from up to an 80% degradation in acceptance length, while maintaining their historical KV cache introduces substantial system overhead. In this paper, we identify the growing historical context as a common source of both problems and introduce DLite, a history-free speculative decoding framework for agentic AI. DLite directly reuses contextual hidden states from the target model and performs local speculative prediction without explicitly maintaining the historical context, transforming an increasingly complex modeling problem into local simple prediction problem. A lightweight sequential head further restores intra-block causal dependencies with low overhead. To effectively train this heterogeneous history-free architecture, we introduce a tailored two-stage training strategy.…
PDF arXiv Code
arXiv cs.CVCodeOct 16▲ 27
Execution Before Memory: Diagnosing Memory Failures in Video World Models
Weiyang Jin, Jiwen Yu, Sihan Xu, Yuwei Niu, Xihui Liu
A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result. Current tests fold these into one number, so a low score is easy to read as forgetting. When the change is not carried out, the hidden state transition cannot appear, so the test is not really a test of memory. We introduce MIST, an evaluation that separates the change from the memory it should leave behind. The model first sets the scene while the change stays hidden, and only later is asked to show it, with leakage before that point kept under control. This separation locates the bottleneck: the model sets the scene but does not carry out the instructed change. The same gap appears in general memory evaluations. On that basis we propose M3-Agent (Make the Missing Move), which recursively revises the details of the input instruction so that the model successfully carries out the requested instruction. Relative to the baseline, it more than triples the MIST reveal score. On the benchmarks, WRBench's score T rises by 26.1% and MBench-T's score U by 52.7%. The method meets the problem from the execution side: it shows…
PDF arXiv Code

Papers

Top tools here

Coming with more sources: stars history

All tools

NVIDIA Dynamo+60% downloads · 15.8k/wk+60.0%
BentoML+30% downloads · 41k/wk+29.7%
MLX+26% downloads · 342.6k/wk+25.5%
Open WebUI3 releases this week
mlx-lm+8% downloads · 140.9k/wk+7.5%

Topics in this field

agent memory · memory construction · term memory248 papers54 this week
gpus · gpu · throughput212 papers32 this week
diffusion language models · language models diffusion · models diffusion language145 papers29 this week
sparse attention · linear attention · attention layers131 papers24 this week
continual learning · catastrophic forgetting · forgetting230 papers22 this week
aware routing · model routing · model llm routing82 papers20 this week

Recently funded

Market

EMode PhotonixPre-seed · Oct 16$1M
MueonSeries A · Oct 15$65M
TrimagnetixSeed · Oct 15$1M
ModalSeries B+ · Oct 14$750M
Salience LabsSeries B+ · Oct 14$125M

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

★ Spotlight this month

arXiv cs.DCOct 15▲ 2

When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Muhammad Ibrahim

Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly back the per-engine cache with a remote tier shared by every engine. We study such a tier in a disaggregated deployment of GLM-5.3, an FP8 mixture-of-experts model with multi-head latent attention (MLA), on 8xB300 nodes running prefill context parallelism (PCP8). Enabling the remote tier (LMCache with a Valkey store) left median time-to-first-token unchanged but raised the 16k-token p99 from 3.96 s to 17.3 s. Replaying a production request stream on an isolated engine, we find that a remote hit took 0.88 s against 0.31 s to recompute the prompt, and that synchronous loading turned a hit-heavy stream into an unstable queue: p99 83.32 s with the GPUs 7% busy. A two-term cost model explains both: a hit pays off only if the tier delivers more than B* = sR (2.53 GB/s for this model and GPU), and a fixed per-hit engine cost (T0 ~ 0.33 s) means that hits on prompts shorter than about 17k tokens cannot beat recompute at any bandwidth. Guided by the model, we (i) shard the MLA KV store across PCP ranks, with a proof that the existing…

PDF arXiv page Details

Recent papers

All in Research →

arXiv cs.CLCodeOct 19▲ 6
Competing Learning in Hybrid Architectures
Xingyu Shen, Yingfa Chen, Ziqing Qiao, Chaojun Xiao, Xu Han +1
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly expressive mixing mechanism while ensuring high throughput by compressing contextual information into a fixed-size state, but underperform softmax attention in contextual information retrieval. In this paper, we reveal a Competing Learning phenomenon where different kinds of mixers compete to learn the same function, and when any layer learns a function, it suppresses the corresponding learning signal for other layers. Layer attribution analysis reveals that under typical data distributions, modern recurrence learns retrieval functions faster than softmax attention, causing attention to fail to learn retrieval in most cases. Stopping weight updates in recurrence in the middle of training helps attention learn retrieval. Based on these results, we propose a staged training procedure for pre-training hybrid architectures on natural language. Empirical results on models up to 1B parameters show that our method results in substantial improvement in language modeling loss, common-sense reasoning, as well as a wide…
PDF arXiv Code
arXiv cs.CLCodeOct 19▲ 106
MemT-1.0: Towards Memory-Native Evolution
Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi +69
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano and MemT-1.0-Flash, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction…
PDF arXiv Code
arXiv cs.AICodeOct 19▲ 7
Remembering Has a Price: Learning Memory Worth under Resource Constraints
Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang, Han-Jia Ye
Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such stringent joint constraints, we find that existing lifelong-memory methods can become ineffective, with several sophisticated approaches offering little advantage over simple retrieval or even no-memory agents. This reveals a more fundamental problem: resource scarcity makes each memory decision more consequential. When only a small amount of past experience can be retained or reused and opportunities for reasoning and recovery are limited, retrieving a relevant but ineffective memory can consume scarce context and hinder downstream execution. The key challenge is therefore not simply to retrieve relevant experience, but to determine which experiences are actually worth retaining and reusing. To address this challenge, we propose TokenWorth, a lightweight online memory framework that learns query-dependent memory worth from sparse execution feedback and applies it consistently to memory retrieval and bounded memory management. Across three LifelongAgentBench environments and both local and…
PDF arXiv Code
arXiv cs.CLCodeOct 17▲ 5
ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction
Yuxuan Zhou, Junyuan Shang, Tianyu Wang, Chunrui Zheng, Zichang Liu +3
Existing Multi-token prediction (MTP) methods are auxiliary by design: the multi-horizon loss mostly trains modules attached to the backbone, and each added horizon costs another module and another pass. We propose Efficient Causal Self-Recursion (ECHO), which removes both costs. The backbone's own final layer predicts every horizon, so the supervision lands on the parameters that generate the next token, and Dynamic Depth Sampling (DDS) keeps deeper horizons affordable by drawing the training depth with probabilities that decay along depth. Future prediction thus becomes part of the autoregressive objective rather than a task attached to it, and the gains follow on both sides of it. In pretraining, added depth converts into downstream accuracy where auxiliary modules saturate, concentrating on reasoning and code at half the MTP training overhead of training every depth. At inference, the pretrained model is its own drafter: it drafts beyond the depth it was trained for, and keeps its draft-target alignment on the open-ended, high-entropy generation where post-hoc drafters lose theirs. The advantage survives a doubled token budget, a repeated pretraining run, and supervised…
PDF arXiv Code
arXiv cs.CLCodeOct 16▲ 21
DLite: History-free Speculative Decoding for Agentic AI
Jiaming Xu, Hanzhen Wang, Tianlang Zhao, Jiewen Xiao, Chengze Yuan +5
Speculative decoding has become a mainstream technique for accelerating large language model (LLM) inference by using a lightweight draft model to generate candidate tokens that are subsequently verified by the target model. However, agentic workloads introduce long and continuously evolving contexts and frequent multi-turn interactions. Under such workloads, we observe that existing draft models suffer from up to an 80% degradation in acceptance length, while maintaining their historical KV cache introduces substantial system overhead. In this paper, we identify the growing historical context as a common source of both problems and introduce DLite, a history-free speculative decoding framework for agentic AI. DLite directly reuses contextual hidden states from the target model and performs local speculative prediction without explicitly maintaining the historical context, transforming an increasingly complex modeling problem into local simple prediction problem. A lightweight sequential head further restores intra-block causal dependencies with low overhead. To effectively train this heterogeneous history-free architecture, we introduce a tailored two-stage training strategy.…
PDF arXiv Code
arXiv cs.CVCodeOct 16▲ 27
Execution Before Memory: Diagnosing Memory Failures in Video World Models
Weiyang Jin, Jiwen Yu, Sihan Xu, Yuwei Niu, Xihui Liu
A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result. Current tests fold these into one number, so a low score is easy to read as forgetting. When the change is not carried out, the hidden state transition cannot appear, so the test is not really a test of memory. We introduce MIST, an evaluation that separates the change from the memory it should leave behind. The model first sets the scene while the change stays hidden, and only later is asked to show it, with leakage before that point kept under control. This separation locates the bottleneck: the model sets the scene but does not carry out the instructed change. The same gap appears in general memory evaluations. On that basis we propose M3-Agent (Make the Missing Move), which recursively revises the details of the input instruction so that the model successfully carries out the requested instruction. Relative to the baseline, it more than triples the MIST reveal score. On the benchmarks, WRBench's score T rises by 26.1% and MBench-T's score U by 52.7%. The method meets the problem from the execution side: it shows…
PDF arXiv Code

Open problems in Inference & serving

Efficient long-horizon context management3 papers raise it · 3 address it
Long-horizon agents need to retain and use relevant information without exceeding finite context windows.
- REMORY: Learning Residual Memory for Context Compactionraises · addresses
- Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agentsraises · addresses
- MemT-1.0: Towards Memory-Native Evolutionraises · addresses
Token-level LLM routing efficiency1 paper raises it · 1 addresses it
Fine-grained token-level routing improves cost-quality trade-offs but strains existing serving systems.
- TokenRouter: Efficient Serving System for Token-Level LLM Routingraises · addresses
Memory-induced sycophancy in agents1 paper raises it · 1 addresses it
Persistent memories can cause agents to over-align with user beliefs, even when they are incorrect or outdated.
- Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancyraises · addresses
Quality gap in parallel token generation2 papers raise it · 2 address it
Diffusion language models generate tokens in parallel but lag behind autoregressive models in quality.
- ALoDLM: Adaptively Looped Diffusion Language Modelsraises · addresses
- Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Modelsraises · addresses
Sparse attention computation overhead1 paper raises it · 1 addresses it
Sparse attention reduces computation but still requires scoring all keys, limiting efficiency gains.
- DoSA: Dots Sparse Attentionraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 54m ago

Inference & serving

Making models fast and cheap to run: serving systems, kernels, KV-cache, speculative decoding, hardware.

256papers this week−15.8% vs last week

All papers · 1.5k With code · 59

Newest Most relevant

1.4k papers this month